三菱電機株式会社 DXイノベーションセンター
【updates】CVPR2023やICCV2023の論文紹介を#CVPR2023,#ICCV2023で行っています。 【upcoming】NeurIPS2023に参加して#NeurIPS2023で論文紹介を行う予定です。
- Posts110posts
- Likes58likes
- Followers365followers
MotionBERT: A Unified Perspective on Learning Human Motion Representations
Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
Scalable Diffusion Models with Transformers
Uncertainty-aware Unsupervised Multi-Object Tracking
Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes
Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis
CO-Net: Learning Multiple Point Cloud Tasks at Once with A Cohesive Network
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection
Mask-Attention-Free Transformer for 3D Instance Segmentation
Rendering Humans from Object-Occluded Monocular Videos
R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras
Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis
Neural Kernel Surface Reconstruction
LATR: 3D Lane Detection from Monocular Images with Transformer
DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving
1 / 6