IJCV 2026 papers on 3D vision
78 of the 477 papers published in IJCV 2026 (16.4%) are on 3D vision, compared with 13.9% at IJCV 2025. They fall into 6 topics.
See IJCV 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
3D generation · 18 papers
- 3D Scene Generation: A Survey (39 citations)
- A Survey on Human Interaction Motion Generation (22 citations)
- Generative Enhancement for 3D Medical Images (22 citations)
- Reconstructing 4D Spatial Intelligence: A Survey (18 citations)
- FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes (16 citations)
- LightOcc: Lightweight Spatial Embedding for Efficient Vision-based 3D Occupancy Prediction (11 citations)
- MaTe3D: Mask-Guided Text-based 3D-Aware Portrait Editing (5 citations)
- Brain3D: Generating 3D Objects from fMRI (1 citation)
- Breaking Redundancy via 3D Sparse Geometry: 3D-aware Neural Compression for Multi-View Videos (1 citation)
- Content-Rhythm Awareness Contrastive Learning for Music-Driven 3D Dance Generation (1 citation)
- DiffPano++: Scalable and Consistent Multi-View Panorama Generation with Spherical Epipolar-Aware Diffusion (1 citation)
- Text2Scenes: Language-Guided Synthesis of Complex Indoor Scenes (1 citation)
and 6 more in the interactive map.
Gaussian splatting · 16 papers
- Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering (167 citations)
- CoSurfGS: 3D Surface Gaussian Splatting with Collaborative Distributed Learning for Large-scale Scene Reconstruction (25 citations)
- GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting (14 citations)
- Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field (9 citations)
- SaLon3R: Structure-Aware Long-Term Feedforward 3D Reconstruction from Unposed Images (6 citations)
- A-TDOM: Active TDOM via On-the-Fly 3DGS (2 citations)
- FPGS: Feed-Forward Semantic-aware Photorealistic Style Transfer of Large-Scale Gaussian Splatting (2 citations)
- DCRR++: Unsupervised Reflection Removal and Novel View Synthesis via Dual-Pixel Guided 3D Gaussian Splatting (1 citation)
- Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors (1 citation)
- RDG-GS: Relative Depth Guidance with Gaussian Splatting for Real-time Sparse-View 3D Rendering (1 citation)
- Boundary-Aware Model with Deformable Feature Warping for Sparse-View Reconstruction
- CurvLoc: Surface Curvature Prompted Gaussian Splatting for Visual Localization
and 4 more in the interactive map.
Depth and stereo · 16 papers
- RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction (22 citations)
- Materialist: Physically Based Editing Using Single-Image Inverse Rendering (15 citations)
- Multi-view Surface Reconstruction Using Normal and Reflectance Cues (5 citations)
- End-to-End LiDAR-Camera Calibration via Multi-Modal Correspondences Estimation and Explicit BEV Alignment (2 citations)
- Atlantis++: Enabling Underwater Depth Estimation with Stable Diffusion and Beyond (1 citation)
- Combining Projected Uncertainty for Self-Supervised Visual Odometry: From Two-Frame to Multi-Frame (1 citation)
- E-RGB-D: Real-Time Event-Based Perception with Structured Light (1 citation)
- Structure-from-motion in micro-image domain for uncalibrated plenoptic 2.0 cameras (1 citation)
- US$$^3$$Net: Ultralightweight Self-Supervised Stereo Matching Network using Depth-Aware Geometric Soft Occlusion (1 citation)
- A Polynomial Formula for the Perspective Four Points Problem
- Convolutional Legendre Memory Unit (ConvLMU) for Stereo Neuromorphic Event-Based Depth Estimation
- DeepTA: High-Speed Deep Camera Translation Averaging with Reverse Direction Invariance
and 4 more in the interactive map.
Human pose estimation · 14 papers
- Deep Learning-Based Object Pose Estimation: A Comprehensive Survey (90 citations)
- TARGO and TARGO-Net: Benchmarking Target-Driven Object Grasping Under Occlusions (12 citations)
- PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds (11 citations)
- A Guide to Structureless Visual Localization (10 citations)
- MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Pose (4 citations)
- Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes (4 citations)
- An Interactive Conversational 3D Virtual Human (3 citations)
- Combining Absolute and Semi-Generalized Relative Poses for Visual Localization (2 citations)
- PosePAL: Efficient Animal Pose Labeling Using Point Trackers (2 citations)
- Are Minimal Radial Distortion Solvers Really Necessary for Relative Pose Estimation? (1 citation)
- Fundamental Constraints on Camera Centers Arising from 3D-2D Matches of Points and Lines (1 citation)
- Pose without Guesses: Generalizable Object Pose Estimation From a Single Reference (1 citation)
and 2 more in the interactive map.
Face and shape · 10 papers
- Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Network (5 citations)
- Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads (4 citations)
- Model-based Metric 3D Shape and Motion Reconstruction of Wild Bottlenose Dolphins in Drone-Shot Videos (4 citations)
- BBoxMaskPose v2: Expanding Mutual Conditioning to 3D (1 citation)
- CAT++: Enhancing 3D Annotations with Hierarchical-Interleaved Encoding and Attention-Conditioned Implicit Representation
- Feed-Forward Multi-view Multi-person Reconstruction with Contrastive Human-Aware 3D Representation
- Locality Optimization Refinement with Deformation for Shape Matching via Functional Maps
- NeuraLeaf: Disentangled Neural Parametric Modeling of Leaf Shape, Deformation, and Appearance
- ShapeRhythm: Personalized and Harmonic Dance Generation Bridging Diverse Bodies and Melodies
- TEPR: Thermal Edge-Prompted Geometry Learning for Multi-View 3D Reconstruction
NeRF and radiance fields · 4 papers
- Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Review (19 citations)
- Progressive Volume Distillation with Active Learning for Efficient NeRF Architecture Conversion (10 citations)
- Learning Generalizable Semantic Radiance Fields with Cross-Reprojection Attention
- RehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editing
