GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.
hub
Mvsplat: Efficient 3d gaussian splatting from sparse multi-view images
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 15roles
background 1polarities
background 1representative citing papers
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
Splats in Splats++ embeds messages into 3DGS via importance-graded SH encryption, hash-grid opacity mapping, and a gradient-gated consistency loss, achieving higher fidelity and robustness than prior methods.
SparseSplat uses entropy-based probabilistic sampling and a specialized point cloud network to generate compact 3D Gaussian maps that retain high rendering quality with far fewer Gaussians than prior feed-forward methods.
PointSplat infers compact Gaussian splats directly in 3D space from input point sets via ray casting and Point-Image Transformer to reduce inter-view redundancy and improve novel-view quality for humans.
Flow Splatting extends 4D Gaussian volumes with time-varying means and covariances, approximates a velocity field, and splats it to render optical flow for supervising dynamic reconstruction from monocular video.
Hand-4DGS introduces the first feed-forward 3D Gaussian Splatting framework for 4D hand reconstruction from egocentric videos, achieving ~60 FPS inference and generalization on H2O and ARCTIC datasets.
SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.
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.
YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.
FLEG reconstructs language-embedded 3D Gaussians from arbitrary input views using a dual-branch distillation framework and a sparse set of semantic Gaussians that requires only 5% of prior embeddings.
Data-centric novel view synthesis models with minimal 3D knowledge and no pose annotations scale better with data volume and outperform traditional bias-driven methods.
VG²GT regresses Gaussian primitive parameters from multi-scale voxel features of a frozen VFM and uses stochastic solid volume rendering for depth supervision to produce geometrically accurate reconstructions that outperform prior methods on DTU, Replica, TAT, and ScanNet.
Long-LRM++ achieves real-time 14 FPS high-fidelity 360-degree scene reconstruction from 32-64 views by using semi-explicit Gaussians plus a light decoder, matching LaCT quality on DL3DV and improving depth prediction.
Turbo-GS accelerates 3D Gaussian Splatting training via dilated rendering of pixel subsets, convergence-aware Gaussian budget allocation, and combined positional-appearance error densification to enable faster 4K fitting with preserved or improved rendering quality.
citing papers explorer
-
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.
-
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
NoPo4D is the first feed-forward system for dynamic 4D Gaussian splatting from unposed multi-view videos, using velocity decomposition supervised by optical flow and a bidirectional motion encoder.
-
Splats in Splats++: Robust and Generalizable 3D Gaussian Splatting Steganography
Splats in Splats++ embeds messages into 3DGS via importance-graded SH encryption, hash-grid opacity mapping, and a gradient-gated consistency loss, achieving higher fidelity and robustness than prior methods.
-
SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Prediction
SparseSplat uses entropy-based probabilistic sampling and a specialized point cloud network to generate compact 3D Gaussian maps that retain high rendering quality with far fewer Gaussians than prior feed-forward methods.
-
PointSplat: Compact Gaussian Splatting via Human-Centric Prediction
PointSplat infers compact Gaussian splats directly in 3D space from input point sets via ray casting and Point-Image Transformer to reduce inter-view redundancy and improve novel-view quality for humans.
-
Learning Efficient 4D Gaussian Representations from Monocular Videos with Flow Splatting
Flow Splatting extends 4D Gaussian volumes with time-varying means and covariances, approximates a velocity field, and splats it to render optical flow for supervising dynamic reconstruction from monocular video.
-
Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos
Hand-4DGS introduces the first feed-forward 3D Gaussian Splatting framework for 4D hand reconstruction from egocentric videos, achieving ~60 FPS inference and generalization on H2O and ARCTIC datasets.
-
Self-Learning Expression Deformations for Data-Efficient Gaussian Avatars
SAGE self-learns Gaussian expression deformations via joint surfel-SDF optimization and self-supervised consistency, enabling comparable avatar quality from single frames, monocular rotations, or one-shot inputs.
-
DelowlightSplat: Feed-Forward Gaussian Splatting for Lowlight 3D Scene Reconstruction
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.
-
You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes
YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.
-
FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation
FLEG reconstructs language-embedded 3D Gaussians from arbitrary input views using a dual-branch distillation framework and a sparse set of semantic Gaussians that requires only 5% of prior embeddings.
-
The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge
Data-centric novel view synthesis models with minimal 3D knowledge and no pose annotations scale better with data volume and outperform traditional bias-driven methods.
-
$\text{VG}^2$GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer
VG²GT regresses Gaussian primitive parameters from multi-scale voxel features of a frozen VFM and uses stochastic solid volume rendering for depth supervision to produce geometrically accurate reconstructions that outperform prior methods on DTU, Replica, TAT, and ScanNet.
-
Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction
Long-LRM++ achieves real-time 14 FPS high-fidelity 360-degree scene reconstruction from 32-64 views by using semi-explicit Gaussians plus a light decoder, matching LaCT quality on DL3DV and improving depth prediction.
-
Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields
Turbo-GS accelerates 3D Gaussian Splatting training via dilated rendering of pixel subsets, convergence-aware Gaussian budget allocation, and combined positional-appearance error densification to enable faster 4K fitting with preserved or improved rendering quality.