3DV 2024
147 papers
The 2024 edition of the 3DV conference featured 165 papers focusing on advancements in 3D computer vision and geometric deep learning. Key research themes included 6D pose estimation, differentiable rendering for occupancy prediction, and the integration of 2D foundation models for open-vocabulary 3D perception. Notable contributions addressed the accuracy-latency trade-off in spatial refinement and explored semantic arithmetic within 3D latent spaces. Research also emphasized the decoupled optimization of geometry and appearance, alongside methods for dynamic scene reconstruction involving topological transitions.
Prolific contributors included Marc Pollefeys, Michael J. Black, and Federico Tombari. Technical trends highlighted neural implicit scene encoding, as demonstrated in NICER-SLAM and RaNeuS, and self-supervision for automotive Lidar point clouds via BEVContrast. Other significant work focused on text-to-3D generation through TextMesh, as well as recovering shape and reflectance under unknown lighting. The proceedings also featured developments in model-free category-level pose estimation and experience replay for continual learning, reflecting a broad interest in both efficiency and generalizability in 3D environments.
Top Research Directions
Research directions most represented by 3DV 2024 papers.
Top Authors
Impactful Papers
Papers from 3DV 2024 that shaped research clusters.
Foundational
Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images
foundational
3D Generation via Latent Space Diffusion
Influential
Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalization
influential
Generalizing Depth Estimation to Unseen
NeRF-Feat: 6D Object Pose Estimation using Feature Rendering
influential
Model Free Generalizable 6D Object Pose
Few-View Object Reconstruction with Unknown Categories and Camera Poses
influential
Resolving Shape Radiance Ambiguity in Sp
Learning Based Infinite Terrain Generation with Level of Detailing
influential
Compositional Generative Models for Mult
PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections
influential
Differentiable Layers for End to End Geo
Physics-based Indirect Illumination for Inverse Rendering
influential
Global Illumination Modeling for Inverse
A Local Appearance Model for Volumetric Capture of Diverse Hairstyles
influential
High Frequency Geometric Complexity in 3
Physics-based Indirect Illumination for Inverse Rendering
influential
Beyond the Lambertian Assumption for Non
SUCRe: Leveraging Scene Structure for Underwater Color Restoration
influential
3D Reconstruction of Textureless Surface
A Local Appearance Model for Volumetric Capture of Diverse Hairstyles
influential
Real Time View Synthesis with 3D Gaussia
Papers
« prev Page 3/3