3DV 2025
150 papers
The 2025 edition of the 3DV conference featured 190 papers focusing on advancements in 3D scene decomposition and real-time spatial perception. Key research directions included the development of decoupled architectures for spatial awareness and the application of geometric priors for structural hallucination. Technical discussions also emphasized the sensitivity of 3D reconstruction processes to initial segmentation stages.
Methodological trends highlighted the integration of diffusion models for 3D object generation and human modeling, as evidenced by research into joint-aware latent diffusion and co-speech gesture generation. The proceedings showcased progress in zero-shot instance segmentation via 3D prompt localization and efficient view synthesis using 3D Gaussian Splatting. Other contributions addressed large-scale structure from motion and 3D registration techniques. Prolific authors contributing to the year's program included researchers such as Andrea Vedaldi, Christian Theobalt, and Luc Van Gool.
Top Research Directions
Research directions most represented by 3DV 2025 papers.
Top Authors
Impactful Papers
Papers from 3DV 2025 that shaped research clusters.
Foundational
RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real- Time Rendering with 900+ FPS
foundational
Pruning Redundant Primitives in 3D Gauss
A Large-Scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining
foundational
Pruning Redundant Primitives in 3D Gauss
Influential
LSE-NeRF: Learning Sensor Modeling Errors for Deblured Neural Radiance Fields with RGB-Event Stereo
influential
Sharp 3D Reconstruction from Motion Blur
MotionDreamer: Exploring Semantic Video Diffusion Features for Zero-Shot 3D Mesh Animation
influential
Bridging the Synthetic to Real Visual Do
iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
influential
Resolving Shape Radiance Ambiguity in Sp
SparseGS: Sparse View Synthesis using 3D Gaussian Splatting
influential
Resolving Geometric Ambiguity in Sparse
MeshUp: Multi-Target Mesh Deformation via Blended Score Distillation
influential
Overcoming the Fixed Topology Constraint
Purposer: Putting Human Motion Generation in Context
influential
The Real World Validation Gap of Synthet
UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video
influential
Material Lighting Disentanglement for 3D
DeforHMR: Vision Transformer with Deformable Cross-Attention for 3D Human Mesh Recovery
influential
Downstream Adaptation via Frozen Feature
ObjectCarver: Semi-automatic segmentation, reconstruction and separation of 3D objects
influential
Reconstructing Complete Geometry from Pa
Papers
« prev Page 3/3