CVPR 2026 accepted papers on 3D vision
772 of the 4,042 papers accepted at CVPR 2026 (19.1%) are on 3D vision, compared with 21.0% at CVPR 2025. They fall into 6 topics.
See CVPR 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
3D generation · 235 papers
- LATTICE: Democratize High-Fidelity 3D Generation at Scale (2 citations)
- Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction (1 citation)
- GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers (1 citation)
- NaTex: Seamless Texture Generation as Latent Color Diffusion (1 citation)
- UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes (1 citation)
- 3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
- 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
- 3D-IDE: 3D Implicit Depth Emergent
- 3D-LATTE: Latent Space 3D Editing from Textual Instructions
- 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
- 3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience
- 4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video
and 223 more in the interactive map.
Gaussian splatting · 196 papers
- DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images (1 citation)
- Faster-GS: Analyzing and Improving Gaussian Splatting Optimization (1 citation)
- GaussianFluent: Gaussian Simulation for Dynamic Scenes with Mixed Materials (1 citation)
- Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting (1 citation)
- RelightAnyone: A Generalized Relightable 3D Gaussian Head Model (1 citation)
- 3D Gaussian Splatting with Self-Constrained Priors for High Fidelity Surface Reconstruction
- 4C4D: 4 Camera 4D Gaussian Splatting
- A Geometric Algebra-Informed 3DGS Framework for Wireless Channel Prediction
- AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D Reconstruction
- Aesthetic Camera Viewpoint Suggestion with 3D Aesthetic Field
- AnchorSplat: Feed-Forward 3D Gaussian Splatting With 3D Geometric Priors
- ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals
and 184 more in the interactive map.
Depth and stereo · 133 papers
- GMT: Effective Global Framework for Multi-Camera Multi-Target Tracking (2 citations)
- Spectrum from Defocus: Fast Spectral Imaging with Chromatic Focal Stack (1 citation)
- 3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding
- AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
- Any Resolution Any Geometry: From Multi-View To Multi-Patch
- Any4D: Unified Feed-Forward Metric 4D Reconstruction
- AVGGT: Rethinking Global Attention for Accelerating VGGT
- BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images
- Beyond Geometry: Artistic Disparity Synthesis for Immersive 2D-to-3D
- Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers
- Breaking the Scalability Limit of Multi-Projector Calibration with Embedded Cameras
- CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography
and 121 more in the interactive map.
Face and shape · 102 papers
- Native and Compact Structured Latents for 3D Generation (4 citations)
- CraftMesh: High-Fidelity Generative Mesh Manipulation via Poisson Seamless Fusion (1 citation)
- Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface (1 citation)
- SAM 3D: 3Dfy Anything in Images (1 citation)
- 3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects
- Affostruction: 3D Affordance Grounding with Generative Reconstruction
- AHS: Adaptive Head Synthesis via Synthetic Data Augmentations
- Animator-Centric Skeleton Generation on Objects with Fine-Grained Details
- ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild
- ART: Articulated Reconstruction Transformer
- Best Segmentation Buddies for Image-Shape Correspondence
- CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image
and 90 more in the interactive map.
Human pose estimation · 86 papers
- FMPose3D: monocular 3D pose estimation via flow matching (1 citation)
- UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation (1 citation)
- A Cross-view Fusion Framework for Robust 6-DoF Grasp Pose Estimation
- ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model
- AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment
- AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion
- Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation
- Breaking the 3D Dataset Bottleneck: Fast Scalable Generation of Aligned 3D Assets from Scratch for Category 6D Pose Estimation and Robotic Grasping
- Bringing Your Portrait to 3D Presence
- CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation
- COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation
- ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation
and 74 more in the interactive map.
NeRF and radiance fields · 20 papers
- Radiance Meshes for Volumetric Reconstruction (1 citation)
- Charge: A Comprehensive Novel View Synthesis Benchmark and Dataset to Bind Them All
- ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
- Evidential Neural Radiance Fields
- Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis
- LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes
- MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
- Multi-view Pyramid Transformer: Look Coarser to See Broader
- NeAR: Coupled Neural Asset-Renderer Stack
- Neural Dynamic GI: Random-Access Neural Compression for Temporal Lightmaps in Dynamic Lighting Environments
- PhysGaia: A Physics-aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis
- PPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction
and 8 more in the interactive map.