LighTROcc: Lightweight 4D Occupancy Forecasting via Instance-Centric 3D Gaussians
cs.CV
Submitted: 2026-10-07
Updated: 2026-10-07
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- ShapeNet: An Information-Rich 3D Model Repository
- FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation
- Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion
- Sparse4D v2: Recurrent Temporal Fusion with Sparse Model
- Sparse4D v3: Advancing End-to-End 3D Detection and Tracking
- FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin
- PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models