3D Vision

This paper introduces SAM-guided masked token prediction, a novel framework for 3D scene understanding that leverages foundation models to significantly improve 3D object detection and semantic segmen…

SA3DIP boosts 3D instance segmentation accuracy by cleverly using 3D spatial and textural cues alongside 2D multi-view masks, overcoming limitations of previous methods.

RobIR: Robust inverse rendering in high-illumination scenes using ACES tone mapping and regularized visibility estimation for accurate BRDF reconstruction.

L1-norm based 3D convolution achieves competitive performance with lower energy consumption and latency compared to traditional methods, as proven through universal approximation theorem and experimen…

ReGS: Real-time reference-based 3D scene stylization using Gaussian Splatting for high-fidelity texture editing and free-view navigation.

Researchers developed a novel method for reconstructing the 3D shape of manipulated garments, achieving superior accuracy compared to existing techniques, particularly for complex, non-rigid deformati…

QUEEN: A novel framework for quantized and efficient streaming of free-viewpoint videos achieving high compression, quality, and speed.

ProvNeRF enhances NeRF reconstruction by modeling per-point provenance as a stochastic field, improving novel view synthesis and uncertainty estimation, particularly in sparse, unconstrained view sett…

ProEdit: High-quality 3D scene editing via progressive subtask decomposition.

Parametric Piecewise Linear Networks (PPLNs) achieve state-of-the-art results in event-based and frame-based computer vision tasks by mimicking biological neural principles.

This paper presents a novel method for analytically extracting meshes from neural implicit surface networks using trilinear interpolation, offering theoretical insights and practical efficiency.

PointMamba: A linear-complexity state space model achieving superior performance in point cloud analysis, reducing computational cost significantly.

PointAD: a novel zero-shot 3D anomaly detection method using CLIP’s strong generalization abilities to identify anomalies in unseen objects by transferring knowledge from both points and pixels.

Point-PRC improves generalizable 3D point cloud analysis by regulating prompt learning to harmonize task-specific and general knowledge within large 3D models.

Single image to physically compatible 3D objects: A new framework ensures 3D models maintain stability and mirror real-world equilibrium states, advancing realism in dynamic simulations and 3D printi…

PHYRECON: A novel neural scene reconstruction method uses differentiable rendering and physics simulation for physically plausible 3D models.

New Pedestrian-Vehicle Collision Pose dataset (PVCP) and Pose Estimation Network (PPSENet) improve pedestrian pre-collision pose estimation from dashcam video.

PCP-MAE enhances point cloud self-supervised learning by cleverly predicting masked patch centers, leading to superior 3D object classification and scene segmentation.

PCoTTA: A novel framework enables multi-task point cloud models to seamlessly adapt to continuously changing target domains during testing, overcoming catastrophic forgetting and error accumulation.

OPUS: a novel, real-time occupancy prediction framework using a sparse set prediction paradigm, outperforms state-of-the-art methods on Occ3D-nuScenes.