REVIEW 9 cited by
StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views
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
We present a novel multi-view implicit surface reconstruction technique, termed StreetSurf, that is readily applicable to street view images in widely-used autonomous driving datasets, such as Waymo-perception sequences, without necessarily requiring LiDAR data. As neural rendering research expands rapidly, its integration into street views has started to draw interests. Existing approaches on street views either mainly focus on novel view synthesis with little exploration of the scene geometry, or rely heavily on dense LiDAR data when investigating reconstruction. Neither of them investigates multi-view implicit surface reconstruction, especially under settings without LiDAR data. Our method extends prior object-centric neural surface reconstruction techniques to address the unique challenges posed by the unbounded street views that are captured with non-object-centric, long and narrow camera trajectories. We delimit the unbounded space into three parts, close-range, distant-view and sky, with aligned cuboid boundaries, and adapt cuboid/hyper-cuboid hash-grids along with road-surface initialization scheme for finer and disentangled representation. To further address the geometric errors arising from textureless regions and insufficient viewing angles, we adopt geometric priors that are estimated using general purpose monocular models. Coupled with our implementation of efficient and fine-grained multi-stage ray marching strategy, we achieve state of the art reconstruction quality in both geometry and appearance within only one to two hours of training time with a single RTX3090 GPU for each street view sequence. Furthermore, we demonstrate that the reconstructed implicit surfaces have rich potential for various downstream tasks, including ray tracing and LiDAR simulation.
Forward citations
Cited by 9 Pith papers
-
AGS: Accelerating 3D Gaussian Splatting SLAM via CODEC-Assisted Frame Covisibility Detection
AGS speeds up 3DGS-SLAM training by measuring frame covisibility from CODEC motion-estimation data, then skipping redundant pose refinements and non-contributory Gaussian computations.
-
M$^\text{4}$World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming
M4World is a controllable multi-view camera+LiDAR driving world model with object-level appearance control, four-step causal streaming, and few-clip long-tail adaptation.
-
Robust 4D Driving Scene Reconstruction from Imperfect Visual Priors
A self-correcting Gaussian scene graph uses semantic attention and adaptive topology updates to reconstruct dynamic driving scenes from noisy video-only priors.
-
ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
ExtraGS combines Gaussian-SDF road surfaces, far-field Gaussians, and spherical-harmonics uncertainty gating to generate geometrically consistent extrapolated driving views.
-
GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting
A camera-only Gaussian-surfel pipeline reconstructs full Waymo scenes, converts them to binary occupancy labels, and trains CVT-Occ to generalize on Occ3D-Waymo and Occ3D-nuScenes at a level close to or above LiDAR-la...
-
GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields
GeoProg3D combines a georeferenced hierarchical 3D language field, geographic vision APIs, and LLM-generated programs to answer natural-language queries about city-scale 3D scenes, and includes a new 952-query benchma...
-
Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering
UGSDF achieves state-of-the-art novel-view rendering of dynamic urban objects without LiDAR or 3D motion annotations by jointly optimizing SDFs and 3D Gaussians under 2D depth and point-tracking priors.
-
CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting
CRUISE reconstructs real V2X driving scenes as editable Gaussians, then shows that training on its generated data improves 3D detection and tracking on the V2X-Seq benchmark.
-
DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes
DrivingGaussian++ reconstructs dynamic surround-view driving scenes and performs training-free multi-task editing (weather, texture, object manipulation) using Gaussians, diffusion models, and LLM-generated trajectories.
Discussion (0). Sign in to comment.