REVIEW 30 cited by
NeRF++: Analyzing and Improving Neural Radiance Fields
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Neural Radiance Fields (NeRF) achieve impressive view synthesis results for a variety of capture settings, including 360 capture of bounded scenes and forward-facing capture of bounded and unbounded scenes. NeRF fits multi-layer perceptrons (MLPs) representing view-invariant opacity and view-dependent color volumes to a set of training images, and samples novel views based on volume rendering techniques. In this technical report, we first remark on radiance fields and their potential ambiguities, namely the shape-radiance ambiguity, and analyze NeRF's success in avoiding such ambiguities. Second, we address a parametrization issue involved in applying NeRF to 360 captures of objects within large-scale, unbounded 3D scenes. Our method improves view synthesis fidelity in this challenging scenario. Code is available at https://github.com/Kai-46/nerfplusplus.
Forward citations
Cited by 30 Pith papers
-
Points as Tori: Fast Pointwise Signed Distance for Point Clouds
Blending closed-form torus SDFs, with per-point coefficients predicted by a shared neural network, yields pointwise signed distance to point clouds without explicit reconstruction.
-
PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur
PRISM3D bootstraps 3D Gaussian Splatting from extreme motion blur via VGGSfM initialization, MCMC densification, and Bézier trajectories, with an event-assisted extension that sets new SOTA.
-
PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping
A self-supervised, physics-regularized neural reconstruction produces high-resolution fetal brain T2 maps at 0.55 T and 1.5 T from multi-echo MRI, with reduced acquisition time.
-
TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
TWINGS applies thin plate splines to warp-align backprojected depth points with triangulated controls for geometrically accurate initialization of sparse-view 3D Gaussian Splatting.
-
LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
An incremental 3D Gaussian Splatting pipeline that jointly optimizes camera poses and scene geometry using MASt3R priors and density-adaptive octree anchors achieves state-of-the-art novel view synthesis on casual lon...
-
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
A decoder-only Transformer with causal attention and cached past-frame features performs incremental 3D reconstruction from streaming images, beating the RNN-based CUT3R on several benchmark metrics.
-
Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields
PATA learns a scene-wise inference time step for spike-based NeRF, cutting estimated energy by up to 68.90% with minimal PSNR loss.
-
Exploring Active Learning for Label-Efficient Training of Semantic Neural Radiance Field
Active learning with a 3D spatial-diversity term cuts annotation cost by over 2x for semantically-aware NeRF training versus random sampling.
-
SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting
SurfaceSplat combines SDF-based coarse meshes with Gaussian splatting to improve sparse-view reconstruction and rendering, but the ablations do not isolate the effect of each component.
-
TimeNeRF: Building Generalizable Neural Radiance Fields across Time from Few-Shot Input Views
A generalizable NeRF that renders novel views of unseen scenes at arbitrary viewpoints and times of day from few input views, without per-scene optimization.
-
HPR3D: Hierarchical Proxy Representation for High-Fidelity 3D Reconstruction and Controllable Editing
HPR3D represents a 3D object as a hierarchy of proxy nodes with per-node texture features, enabling compact reconstruction and multi-scale drag-based editing.
-
RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
RegGS aligns locally generated 3D Gaussian maps using a Sinkhorn-approximated mixture Wasserstein distance, improving pose estimation and novel view synthesis from sparse unposed views.
-
A Probability-guided Sampler for Neural Implicit Surface Rendering
An SDF-driven ray and pixel sampler plus new surface losses modestly improve NeuS and Neuralangelo on object-centric datasets, without code release.
-
On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
An incremental pipeline jointly estimates camera poses and 3D Gaussian primitives at capture speed, handling large ordered photo sequences with anchors and progressive merging.
-
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
A new 3D language Gaussian Splatting method that clusters per-object multi-view CLIP features and reweights them to capture view-dependent semantics, improving direct 3D open-vocabulary segmentation.
-
Structure from Collision
A new model, SfC-NeRF, estimates hidden internal cavities of deformable objects from collision videos, using physics constraints and known mass, and demonstrates the idea on 115 simulated objects.
-
Triangle Splatting for Real-Time Radiance Field Rendering
A triangle-soup representation with a compact normalized window function is optimized end-to-end and beats Gaussian and convex splatting baselines on LPIPS while rendering at real-time rates.
-
Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting
A proxy mesh rendered through hardware rasterization provides a cheap occlusion depth prior that culls hidden anchors at inference and guides densification at training, giving Octree-GS-like MLP splatting a 3 to 4x sp...
-
Effective Gaussian Management for High-fidelity Scene Reconstruction
A Gaussian management framework with conflict-aware attribute decoupling, adaptive spherical-harmonic orders, and confidence-based SDF normal distillation improves appearance quality while cutting model size, at rough...
-
Towards Integrating Multi-Spectral Imaging with Gaussian Splatting
Jointly optimizing RGB and four additional spectral bands in one 3D Gaussian Splatting model, after an RGB-only warm-up and with spectrum-aware densification, outperforms per-band models and slightly improves RGB via ...
-
SERES: Semantic-aware neural reconstruction from sparse views
A semantic-aware implicit reconstruction method claims 44% and 20% lower Chamfer distance than SparseNeuS and VolRecon, and 69%/68% error reductions as a NeuS/Neuralangelo plugin.
-
scI2CL: Effectively Integrating Single-cell Multi-omics by Intra- and Inter-omics Contrastive Learning
The abstract claims a state-of-the-art single-cell multi-omics integration method with new cell-subtype and trajectory findings, but the supplied full text is a different paper.
-
GeMS: Efficient Gaussian Splatting for Extreme Motion Blur
GeMS/GeMS-E replaces COLMAP with the learned SfM method VGGSfM, adds MCMC-based Gaussian optimization and joint camera-trajectory fitting, and reconstructs 3D scenes from extreme motion blur with or without events.
-
MZEN: Multi-Zoom Enhanced NeRF for 3-D Reconstruction with Unknown Camera Poses
MZEN is a NeRF training schedule that handles multi-zoom image sets with a zoom-scaled camera model and a bootstrap-register-refine pose strategy, claiming large gains on a new eight-scene benchmark.
-
HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity
HiNeuS builds accurate 3D surfaces from photos by combining SDF-based visibility checks, local planar regularization, and rendering-error-weighted Eikonal constraints, reporting SOTA on several benchmarks.
-
TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering
TraGraph-GS partitions large scenes by graph structure of image feature matches, trains local Gaussian splatting models per region, and blends them progressively for novel view rendering, reporting higher PSNR than pr...
-
Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting
Intern-GS improves sparse-view 3D Gaussian Splatting by initializing from DUSt3R dense point clouds and regularizing with depth and diffusion-refined pseudo-views, achieving state-of-the-art results on three benchmarks.
-
CTRL-GS: Cascaded Temporal Residue Learning for 4D Gaussian Splatting
CTRL-GS represents dynamic Gaussian scenes as cascaded video-segment-frame residuals, improving reconstruction quality over 4D-GS on several dynamic-view benchmarks.
-
Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstruction
A 3DGS surface reconstruction method that enforces multi-view distance and normal consistency between nearby views to reduce geometry drift.
-
Reconstructing 4D Spatial Intelligence: A Survey
A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.
Discussion (0). Sign in to comment.