{"total":46,"items":[{"citing_arxiv_id":"2607.01164","ref_index":20,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation","primary_cat":"cs.LG","submitted_at":"2026-07-01T16:48:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An explicit model using learned 3D Gaussians for volume compression encodes geometry explicitly and outperforms implicit neural representations on unstructured volumes with faster training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31764","ref_index":21,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics","primary_cat":"cs.GR","submitted_at":"2026-06-30T14:51:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"NURBS Splatting represents rational splines as continuous Gaussian fields sampled along the curve to enable stable differentiable rendering of vector graphics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.31065","ref_index":23,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Diffusion-Based Material Regularization for Physics-Based Inverse Rendering","primary_cat":"cs.CV","submitted_at":"2026-06-30T02:52:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A regularization technique that treats diffusion model outputs as a similarity kernel during material optimization in inverse rendering, enabling joint reconstruction of geometry, materials, and illumination that satisfies the rendering equation and generalizes to new lighting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28826","ref_index":11,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"RefGlass-GS: A UAV-Enabled Fusion Framework for Photorealistic, Semantic and Interactive Digitization of Reflective Glass Facades via Gaussian Splatting","primary_cat":"cs.CV","submitted_at":"2026-06-27T09:21:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RefGlass-GS is a fusion framework using UAV data, MAP-based panel segmentation, viewpoint optimization, and modified Gaussian Splatting with Reflection MLP to achieve improved photorealistic and semantic modeling of reflective glass facades.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26985","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Vis4GS: A Visual Analytic Tool for 3D Gaussian Splatting Reconstruction","primary_cat":"cs.GR","submitted_at":"2026-06-25T12:59:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Vis4GS is a multi-view visual analytics system for diagnosing 3DGS reconstruction artifacts by linking scene-level issues to primitive-level properties, view coverage, and optimization history.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25183","ref_index":19,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Low-Cost Continuous-Wave Diffusive Microtomography with Fiber-Scanned White-Light Illumination","primary_cat":"physics.optics","submitted_at":"2026-06-23T21:19:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Low-cost CWDT system with fiber-scanned illumination and ML-tuned forward model yields qualitative volumetric reconstructions from cleared poplar, scattering phantoms, and fungal samples.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24361","ref_index":12,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks","primary_cat":"cs.CV","submitted_at":"2026-06-23T09:51:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper releases SignNet-1M, a 1M-scale augmented dataset for ASL, CSL and DGS with 3DGS and diffusion-based variations, plus benchmarks showing improved cross-shift generalization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24180","ref_index":79,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Deep Learning Approaches for 3D Medical Scene Completion: From Geometric Modeling to Generative Paradigms","primary_cat":"cs.CV","submitted_at":"2026-06-23T06:05:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A literature survey that compiles ten years of 3D scene completion research, builds a taxonomy of representation paradigms, and outlines a future research agenda.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21270","ref_index":60,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering","primary_cat":"physics.optics","submitted_at":"2026-06-19T09:47:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"3D Gaussian transient rendering enables NLOS imaging from arbitrary relay geometries in both confocal and non-confocal setups, achieving SOTA on real measurements.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20131","ref_index":27,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields","primary_cat":"cs.CV","submitted_at":"2026-06-18T11:55:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TriFlow synthesizes nearest-vertex vector fields via flow-matching to generate artist-like 3D mesh topology, then extracts meshes via clustering and topology-aware QEM simplification.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.18734","ref_index":21,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Point-Cloud-Assistant Localized Statistical Channel Prediction by Tangent Gaussian Splatting","primary_cat":"eess.SP","submitted_at":"2026-06-17T06:23:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PC-TGS extrapolates APS to unmeasured grids by modeling scatterers as anisotropic 3D Gaussians from LiDAR data, using tangent-plane projection and depth-aware splatting with a closed-form integration.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.13364","ref_index":21,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"VideoMDM: Towards 3D Human Motion Generation From 2D Supervision","primary_cat":"cs.LG","submitted_at":"2026-06-11T13:49:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VideoMDM learns coherent 3D motion manifolds from 2D supervision alone by using a pretrained lifter as noisy teacher, depth-weighted 2D reprojection loss, and adapted regularizers, nearly matching fully 3D-supervised performance on HumanML3D.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11841","ref_index":18,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Scene-Adaptive Nonlinear Tone Curves for Pseudo Ground-Truth Generation in Low-Light 3D Gaussian Splatting","primary_cat":"cs.CV","submitted_at":"2026-06-10T09:20:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Scene-adaptive nonlinear tone curves (ASE and AP3) with percentile normalisation and offset outperform linear gain for pseudo-GT generation in low-light 3DGS, delivering PSNR gains up to 4.34 dB on LOM and 3.25 dB on RealX3D across 21 scenes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10473","ref_index":35,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"AnisoLift: Anisotropic Latent Representations for Coarse Particle Liquid Enhancement","primary_cat":"cs.GR","submitted_at":"2026-06-09T06:42:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"AnisoLift augments coarse particles with anisotropic ellipsoids and predicts residual state corrections to improve fidelity to high-resolution liquid flows.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09794","ref_index":9,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Beyond Spherical Harmonics: Rethinking Appearance Models for Radiance Reconstruction","primary_cat":"cs.CV","submitted_at":"2026-06-08T17:50:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces Normalized Anisotropic Spherical Gabor function for efficient high-frequency view-dependent appearance modeling in radiance fields, claiming superior quality to low-order spherical harmonics with up to 5x better memory efficiency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07179","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"EvoGS: Constructing Continuous-Layered Gaussian Splatting with Evolution Tree for Scalable 3D Streaming","primary_cat":"cs.CV","submitted_at":"2026-06-05T11:44:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EvoGS proposes the first continuous-layering 3D Gaussian Splatting representation via an Evolution Tree to reduce splat redundancy and transmission costs for scalable streaming.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02961","ref_index":12,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"AtlasGS: Brain MRI Spatial Resolution Harmonization With Shared Gaussian Geometry","primary_cat":"eess.IV","submitted_at":"2026-06-01T23:41:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AtlasGS uses shared subject-specific Gaussian geometry learned from isotropic scans to achieve through-plane super-resolution and multi-modal harmonization in brain MRI with reported state-of-the-art fidelity on UK Biobank, GBM, and ABCD datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02058","ref_index":16,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"TIDES: Time-Derivative Event Simulation via Deformable Reconstruction","primary_cat":"cs.CV","submitted_at":"2026-06-01T10:49:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TIDES simulates realistic event camera streams in continuous time via dynamic Gaussian splatting with adaptive occlusion handling and sensor artifact modeling, claiming SOTA fidelity and better downstream transfer than prior methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31534","ref_index":14,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Feature-Optimized Vision for Adaptive 3D Scene Reconstruction","primary_cat":"cs.CV","submitted_at":"2026-05-29T16:49:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An adaptive multi-criteria feature selection policy for 3D scene reconstruction that outperforms random, texture-only, and uniform-grid baselines on synthetic multi-view tests for completeness and RMSE.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.29452","ref_index":12,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Comparative evaluation of photogrammetric reconstruction methods and 3D Gaussian Splatting for road surface roughness analysis","primary_cat":"cs.CV","submitted_at":"2026-05-28T06:47:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"COLMAP shows highest micro-texture sensitivity while open-source tools prove viable for relative road roughness estimation from images.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26638","ref_index":15,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"HyperSim: A Holistic Sim-To-Real Framework For Robust Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2026-05-26T07:19:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HyperSim reports 80% and 95% sim-to-real success on two manipulation policies across 400 real executions by combining synthetic environment synthesis, adversarial trajectories, and co-training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26629","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"DelowlightSplat: Feed-Forward Gaussian Splatting for Lowlight 3D Scene Reconstruction","primary_cat":"cs.CV","submitted_at":"2026-05-26T07:05:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DelowlightSplat adds a lightweight Lowlight Adapter and cost-volume multi-view inference to feed-forward Gaussian splatting, enabling direct prediction of clean 3D Gaussians from degraded lowlight context views.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24964","ref_index":4,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"ConFi-GS Confidence-Guided High-Frequency Injection for 3D Gaussian Splatting Super-Resolution","primary_cat":"cs.CV","submitted_at":"2026-05-24T09:30:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Proposes a reliability-aware frequency modeling framework using geometry-guided detail-demand prior and frequency-aware reliability map to guide high-frequency detail injection in low-resolution 3DGS, with a unified optimization scheme that improves fidelity on benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23555","ref_index":27,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos","primary_cat":"cs.CV","submitted_at":"2026-05-22T12:20:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TrioMan is a tri-module data augmentation framework using a Generator for pose/camera perturbations, a Refiner with one-step diffusion, and an Examiner with dual-branch attention to improve 3D avatar learning from monocular videos, claiming better results than prior methods on two benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20460","ref_index":45,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning","primary_cat":"cs.GR","submitted_at":"2026-05-19T20:13:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HyperBones trains a reduced-space neural dynamics model with bone-driven coarse simulation and CNN-based wrinkle recovery to produce plausible garment motion at 300+ FPS using physics supervision without an external simulator.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17131","ref_index":42,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation","primary_cat":"cs.CV","submitted_at":"2026-05-16T19:37:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":1.0,"formal_verification":"none","one_line_summary":"A survey that categorizes deep learning models for point cloud tasks by backbone architecture, evaluates benchmark performance, and outlines challenges and future research directions.","context_count":1,"top_context_role":"method","top_context_polarity":"background","context_text":"This shifts the point patches to the local reference point and so makes them unbiased by the overall structure. Next, these point patches are fed through a mini-PointNet [11] that projects the point patches to point embeddings (pretty similar to the PointNet++). These point embeddings are then fed into a discrete variational autoencoder (discrete VAE) [42, 76], which is tasked with respective point patch reconstruction. DGCNN [105] is employed as the encoder of the discrete VAE. Once training is complete, the latent space representations produced by the encoder serve as compact tokens for the respective point patches. As a result, the decoder is no longer required during inference, and the encoder effectively functions as a tokenizer."},{"citing_arxiv_id":"2605.17011","ref_index":3,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Topo-GS: Continuous Volumetric Embedding of High-Dimensional Data via Topological Gaussian Splatting","primary_cat":"cs.GR","submitted_at":"2026-05-16T14:21:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Topo-GS repurposes 3D Gaussian Splatting with local geometric constraints and topology-aware losses to produce continuous volumetric embeddings of high-dimensional data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15324","ref_index":7,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Eff-WRFGS: Efficient Wireless Radiance Field Using 3D Gaussian Splatting","primary_cat":"eess.SP","submitted_at":"2026-05-14T18:38:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Eff-WRFGS prunes 3D Gaussian primitives via learnable masks to deliver up to 44x storage reduction and 7x faster rendering for wireless radiance fields on the NeRF² dataset with marginal quality loss.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11913","ref_index":12,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization","primary_cat":"cs.CV","submitted_at":"2026-05-12T10:27:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Vector Scaffolding uses Interior Gradient Aggregation, Progressive Stratification, and Rapid Inflation Scheduling to achieve 2.5x faster optimization and up to 1.4 dB higher PSNR in differentiable image vectorization.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"methods that sequentially add paths [17] or rely on external diffusion priors [23], we directly stabilize parallel optimization of closed Bézier curves without any external model. This simple framework yields an order-of-magnitude speedup over previous hierarchy-based methods [23] with+1 dBPSNR improvements as shown in Figure 1b and Table 2. 2.2 Gaussian Splatting and Representation Learning 3D Gaussian Splatting (3DGS) [12, 33] has recently emerged as an efficient explicit representation for neural rendering and novel view synthesis. Its dif- ferentiable tile-based rasterization pipeline enables high-fidelity rendering with real-time performance. The efficiency and flexibility of this representation have inspired numerous extensions, including dynamic scene modeling [16,24], gener-"},{"citing_arxiv_id":"2605.11266","ref_index":7,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives","primary_cat":"cs.CV","submitted_at":"2026-05-11T21:43:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PG-3DGS couples 3D Gaussian Splatting with differentiable physics so that optimized shapes satisfy both visual fidelity and physical objectives such as pouring and aerodynamic lift, with real-world 3D-printed validation.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"Reconstructing 3D objects from 2D images has become a practical primitive for computer vision, robotics, and embodied AI. Recent neural and explicit radiance-field methods can infer detailed geometry and appearance from multi-view supervision, enabling high-fidelity novel-view rendering and fast optimization of 3D representations (e.g., NeRF [6] and 3D Gaussian Splatting [7]). In parallel, text- and image-conditioned 3D generation has progressed rapidly by optimizing 3D representations through differentiable rendering (e.g., DreamFusion/Magic3D-style score distillation) [8, 9]. A shared theme across these directions isinverse graphics: when rendering is differentiable, gradients from image-space objectives can be back-propagated"},{"citing_arxiv_id":"2605.09216","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Continuum Robot Modeling with Action Conditioned Flow Matching","primary_cat":"cs.RO","submitted_at":"2026-05-09T23:22:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A conditional point-cloud flow matching model maps motor actuation to 3D geometry of tendon-driven continuum robots and outperforms prior self-modeling methods on simulated and real 2- and 3-module hardware.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"ing conditional 3D implicit functions.arXiv preprint arXiv:2305.02463, 2023. doi: 10.48550/arXiv.2305. 02463. URL https://arxiv.org/abs/2305.02463. [23] Bernhard Kerbl, Georgios Kopanas, Thomas Leimk ¨uhler, and George Drettakis. 3D gaussian splatting for real-time radiance field rendering.ACM Transactions on Graphics, 42(4):139:1-139:14, 2023. doi: 10.1145/3592433. [24] Fouzia Khan, Roy J. Roesthuis, and Sarthak Misra. Force sensing in continuum manipulators using fiber bragg grating sensors. InProceedings of the IEEE/RSJ Inter- national Conference on Intelligent Robots and Systems (IROS), pages 2531-2536, 2017. doi: 10.1109/IROS. 2017.8206073. [25] Clara G. Kierbel, Nicola Perugini, and Matteo Russo. A comparison of monolithic 3D-printed tendon-driven"},{"citing_arxiv_id":"2605.08035","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"PropSplat: Map-Free RF Field Reconstruction via 3D Gaussian Propagation Splatting","primary_cat":"eess.SP","submitted_at":"2026-05-08T17:24:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PropSplat uses optimized 3D Gaussians initialized on transmitter-receiver paths to achieve lower RMSE than NeRF2, GSRF, and WRF-GS+ on outdoor drive-test and indoor BLE datasets while enabling map-free RF reconstruction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06876","ref_index":2,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting","primary_cat":"cs.CV","submitted_at":"2026-05-07T19:23:16+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AdpSplit adaptively splits Gaussians using pixel-error statistics to reduce 3DGS training time by 9-22% without quality loss.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"The ADC accumulates image-space gradients for visible Gaussians. At each densification interval, it first computes the average gradient statistic gi for each Gaussian. Among high-gradient Gaussians, those with small spatial scale are cloned, while those with large spatial scale are split. The split candidate setSis defined as i∈ S ⇐ ⇒g i ≥τ g ∧max(s i)> τ s,(2) whereτ g is the densification gradient threshold andτ s is the scale threshold. For each selected parent Gi, the vanilla split operator generates a fixed number N of children, with N= 2 by default. Each child n is placed near the parent by sampling an offset from the parent's Gaussian distribution: δi,n ∼ N(0,diag(s 2 i )),µ ′ i,n =µ i +R iδi,n.(3)"},{"citing_arxiv_id":"2605.06063","ref_index":55,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures","primary_cat":"cs.GR","submitted_at":"2026-05-07T11:46:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Avatar appearance and facial presentation systematically bias perceptual judgments of synthesized co-speech gestures.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05664","ref_index":24,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes","primary_cat":"cs.CV","submitted_at":"2026-05-07T04:41:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"S2C-3D reconstructs complete high-fidelity 3D scenes from as few as 6-8 images by finetuning a diffusion model on scene data, applying consistency-conditioned sampling, and planning trajectories for full coverage.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05513","ref_index":13,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Age Verification in the Web -- Holy Grail to Control Access to Restricted Content","primary_cat":"cs.CR","submitted_at":"2026-05-06T23:29:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A privacy-preserving age verification approach for the web is proposed by adapting open cryptographic standards like Privacy Pass to let users prove age via trusted providers without special software or centralized data collection.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03337","ref_index":7,"ref_count":3,"confidence":0.88,"is_internal_anchor":false,"paper_title":"FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles","primary_cat":"cs.CV","submitted_at":"2026-05-05T03:57:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FreeTimeGS++ improves dynamic scene reconstruction by identifying emergent temporal partitioning and photometric-motion decoupling in 4DGS, then applying targeted techniques for reduced run-to-run variance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00804","ref_index":49,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Prop-Chromeleon: Adaptive Haptic Props in Mixed Reality through Generative Artificial Intelligence","primary_cat":"cs.HC","submitted_at":"2026-05-01T17:45:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A generative-AI pipeline dynamically generates and anchors virtual assets to match the shape of physical props, enabling adaptive passive haptics in MR that users rate higher in realism, immersion, and enjoyment than static baselines.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[47] Bernhard Kerbl, Georgios Kopanas, Thomas Leimkuehler, and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering.ACM Trans. Graph.42, 4, Article 139 (jul 2023), 14 pages. doi:10.1145/3592433 [48] S. J. Lederman and R. L. Klatzky. 2009. Haptic perception: A tutorial.Attention, Perception, & Psychophysics71, 7 (01 Oct 2009), 1439-1459. doi:10.3758/APP.71.7. 1439 [49] Jaewook Lee, Andrew D. Tjahjadi, Jiho Kim, Junpu Yu, Minji Park, Jiawen Zhang, Jon E. Froehlich, Yapeng Tian, and Yuhang Zhao. 2024. CookAR: Affordance Augmentations in Wearable AR to Support Kitchen Tool Interactions for People with Low Vision. InProceedings of the 37th Annual ACM Symposium on User Interface Software and Technology(Pittsburgh, PA, USA)(UIST '24)."},{"citing_arxiv_id":"2604.24316","ref_index":14,"ref_count":2,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Large-Scale Photogrammetric Documentation of St. John's Co-Cathedral: A Workflow for Cultural Heritage Preservation","primary_cat":"cs.GR","submitted_at":"2026-04-27T11:06:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A complete multi-modal photogrammetry pipeline that produced a 25-30 billion triangle 3D model of St. John's Co-Cathedral while addressing reflective surfaces and low-light conditions through strategic capture, AI denoising, and hybrid reconstruction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19423","ref_index":51,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Allow Me Into Your Dream: A Handshake-and-Pull Protocol for Sharing Mixed Realities in Spontaneous Encounters","primary_cat":"cs.HC","submitted_at":"2026-04-21T12:53:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TouchPort collapses the multi-stage process of discovering, consenting to, and syncing mixed reality encounters into one embodied handshake-and-pull gesture.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"TouchPort:2 gestures,∼3-5s succeeded by hiding its protocol behind one tap. Embodied interac- tion carries more social meaning per unit time than screen-based dialogs [7, 32]. Why embodied instead of screen-based.MR encounters are bodily. A gesture is visible to participants and bystanders simultaneously- serving as both consent mechanism and social indicator [ 51, 79]. Screen-based consent breaks immersion and communicates nothing to nonparticipants. Why the handshake.It is among the most universally recog- nized gestures of mutual agreement. It carries built-in reciprocity, dense cultural meaning (greeting, partnership, trust) [36], and cre- ates a physical anchor for the digital transition. The handshake also"},{"citing_arxiv_id":"2604.14928","ref_index":14,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting","primary_cat":"cs.CV","submitted_at":"2026-04-16T12:13:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A hybrid Gaussian-hash-grid representation with latent features and hard opacity falloffs reconstructs scenes more accurately than prior Gaussian splatting methods while using an order of magnitude fewer primitives.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13856","ref_index":22,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image","primary_cat":"cs.CV","submitted_at":"2026-04-15T13:24:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Any3DAvatar reconstructs full-head 3D Gaussian avatars from one image via one-step denoising on a Plücker-aware scaffold plus auxiliary view supervision, beating prior single-image methods on fidelity while running substantially faster.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"methods [26] are largely optimization-based, where multi-view observations are fitted into a canonical space to recover identity- consistent head geometry and appearance. Later approaches in- corporate NeRF-style representations, which significantly improve rendering realism and enable higher-quality reconstruction of chal- lenging regions such as hair and accessories [ 22]. More recent methods [46] further combine 3DGS and mesh priors in a joint optimization framework, pushing reconstruction and rendering quality to high resolutions (e.g., around 2K). Recently, the field has been shifting toward less restrictive and more efficient settings, moving from camera-constrained optimization pipelines to feed- forward reconstruction with weaker or no explicit camera-pose"},{"citing_arxiv_id":"2604.13340","ref_index":6,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"MSGS: Multispectral 3D Gaussian Splatting","primary_cat":"cs.CV","submitted_at":"2026-04-14T23:03:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MSGS augments 3D Gaussian Splatting with spectral radiance via per-band spherical harmonics and dual-loss supervision to improve multispectral view synthesis quality and consistency over RGB-only baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13333","ref_index":4,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"SSD-GS: Scattering and Shadow Decomposition for Relightable 3D Gaussian Splatting","primary_cat":"cs.CV","submitted_at":"2026-04-14T22:47:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SSD-GS decomposes 3D Gaussian Splatting reflectance into diffuse, specular, shadow, and subsurface scattering using a dipole scattering module, occlusion-aware shadows, and anisotropic Fresnel specular for photorealistic novel lighting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16449","ref_index":9,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Gaussian Field Representations for Turbulent Flow: Compression, Scale Separation, and Physical Fidelity","primary_cat":"physics.flu-dyn","submitted_at":"2026-04-07T18:40:57+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Gaussian primitives compress 3D Taylor-Green vortex flows at ratios over 1000x while preserving velocity but degrading enstrophy, with anisotropic extensions recovering small-scale vortical structures better than baseline or other variants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.04874","ref_index":21,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction","primary_cat":"cs.CV","submitted_at":"2026-04-06T17:24:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Free-Range Gaussians uses flow matching over Gaussian parameters to predict non-grid-aligned 3D Gaussians from multi-view images, enabling synthesis of plausible content in unobserved regions with fewer primitives than grid-aligned methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}