3D Vision

DCDepth achieves state-of-the-art monocular depth estimation by progressively predicting depth in the frequency domain via DCT, capturing local correlations and global context effectively.

DC-Gaussian: A novel method generates high-fidelity novel views from dashcam videos by addressing common windshield obstructions (reflections, occlusions) using adaptive image decomposition, illumina…

CryoSPIN revolutionizes ab-initio cryo-EM reconstruction with semi-amortized pose inference, achieving faster and more accurate 3D structure determination.

CRAYM: Neural field optimization via camera RAY matching enhances 3D reconstruction by using camera rays, not pixels, improving both novel view synthesis and geometry.

NerPE: continuous heatmap regression via implicit neural representation resolves the accuracy-limiting quantization errors in human pose estimation, achieving sub-pixel precision.

ContextGS: Revolutionizing 3D scene compression with an anchor-level autoregressive model, achieving 15x size reduction in 3D Gaussian Splatting while boosting rendering quality.

CGFormer: a novel voxel transformer boosting semantic scene completion accuracy by using context-aware queries and 3D deformable attention, outperforming existing methods on SemanticKITTI and SSCBench…

Novel implicit field representation accurately reconstructs multi-person interaction geometry in 3D, simultaneously capturing occupancy, instance IDs, and contact fields, surpassing existing methods.

CoFie: A novel local geometry-aware neural surface representation dramatically improves accuracy and efficiency in 3D shape modeling by using coordinate fields to compress local shape information.

CAT3D: Generate high-quality 3D scenes from as little as one image using a novel multi-view diffusion model, outperforming existing methods in speed and quality.

Binocular-guided 3D Gaussian splatting with self-supervision generates high-quality novel views from sparse inputs without external priors, significantly outperforming state-of-the-art methods.

BetterDepth: A plug-and-play diffusion refiner boosts zero-shot monocular depth estimation by adding fine details while preserving accurate geometry.

Hypergraph-Based Assembly Fuzzy Representation (HAFR) excels at open-set 3D object retrieval by using part-level shapes and fuzzy representations to overcome challenges posed by unseen object categori…

Unsupervised Articulated Object Modeling using Conditional View Synthesis learns pose and part segmentation from only two object observations, achieving significantly better performance than previous …

Animate3D animates any 3D model using multi-view video diffusion, achieving superior spatiotemporal consistency and straightforward mesh animation.

AlphaTablets revolutionizes 3D planar reconstruction from monocular videos with its novel rectangle-based representation featuring continuous surfaces and precise boundaries, achieving state-of-the-ar…

Boosting Multi-Scene Pose Regression: Novel methods activate transformer self-attention, significantly improving camera pose estimation accuracy and efficiency.

UniSeg3D: One model to rule them all! This unified framework masters six 3D segmentation tasks (panoptic, semantic, instance, interactive, referring, and open-vocabulary) simultaneously, outperforming…

UniDC framework achieves universal depth completion across various sensors and scenes using minimal labeled data, leveraging a foundation model and hyperbolic embedding for enhanced generalization.

This paper introduces a novel, robust inlier identification algorithm for point cloud registration that leverages lo-minimization.