REVIEW 7 cited by
RenderWorld: World Model with Self-Supervised 3D Label
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
End-to-end autonomous driving with vision-only is not only more cost-effective compared to LiDAR-vision fusion but also more reliable than traditional methods. To achieve a economical and robust purely visual autonomous driving system, we propose RenderWorld, a vision-only end-to-end autonomous driving framework, which generates 3D occupancy labels using a self-supervised gaussian-based Img2Occ Module, then encodes the labels by AM-VAE, and uses world model for forecasting and planning. RenderWorld employs Gaussian Splatting to represent 3D scenes and render 2D images greatly improves segmentation accuracy and reduces GPU memory consumption compared with NeRF-based methods. By applying AM-VAE to encode air and non-air separately, RenderWorld achieves more fine-grained scene element representation, leading to state-of-the-art performance in both 4D occupancy forecasting and motion planning from autoregressive world model.
Forward citations
Cited by 7 Pith papers
-
Semantic Causality-Aware Vision-Based 3D Occupancy Prediction
A class-conditional gradient loss (Causal Loss) plus channel-grouped lifting, learnable camera offsets, and normalized convolution raises Occ3D mIoU by 1.2/0.8 points and cuts the camera-noise mIoU drop from 32% to 7%.
-
COME: Adding Scene-Centric Forecasting Control to Occupancy World Model
COME adds a scene-centric forecasting branch as a ControlNet-style condition to a diffusion occupancy world model, improving static-scene consistency and beating prior methods on Occ3D-nuScenes while hiding a stronger...
-
GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
GeoDrive conditions a frozen video diffusion model on a 3D-rendered version of the requested ego trajectory, cutting trajectory-following error by 42% versus Vista while using 99.7% less training data.
-
A Definition and Roadmap for World Models
A perspective article defining world models as finite-resource compression of physical state transitions and outlining a roadmap toward physical AGI via unified representations and interactive simulators.
-
ICM-Fusion: In-Context Meta-Optimized LoRA Fusion for Multi-Task Adaptation
ICM-Fusion uses a conditional VAE plus task-vector guidance to fuse multiple LoRA adapters into one model, reporting marginal average gains on vision and language benchmarks and larger gains in a few-shot long-tail setup.
-
QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction
QuadricFormer represents 3D scenes as a probabilistic mixture of superquadrics, improving accuracy and efficiency over Gaussian-based occupancy prediction on nuScenes.
-
Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities
Foundation-model perception for autonomous driving is surveyed through four capability lenses: generalized knowledge, spatial understanding, multi-sensor robustness, and temporal understanding.
Discussion (0). Sign in to comment.