3D Vision

Effective rank regularization enhances 3D Gaussian splatting, resolving needle-like artifacts and improving 3D model quality.

4DGF, a novel neural scene representation, achieves interactive-speed novel view synthesis for large-scale dynamic urban areas by efficiently combining 3D Gaussians and neural fields.

Self-supervised dual-frame fluid motion estimation achieves superior accuracy with 99% less training data, using a novel zero-divergence loss and dynamic velocimetry enhancement.

Dual-Diffusion boosts binocular 3D human pose estimation accuracy by simultaneously denoising 2D and 3D pose uncertainties using a diffusion model.

Dual encoder GAN inversion achieves high-fidelity 3D head reconstruction from single images by cleverly combining outputs from encoders specialized for visible and invisible regions, surpassing existi…

DreamMesh4D: Generating high-fidelity dynamic 3D meshes from monocular video using a novel Gaussian-mesh hybrid representation and adaptive hybrid skinning.

DOGS: Distributed-Oriented Gaussian Splatting accelerates large-scale 3D reconstruction by distributing the training of 3D Gaussian Splatting models across multiple machines, achieving 6x faster train…

DN-4DGS: Real-time dynamic scene rendering is revolutionized by a denoised deformable network with temporal-spatial aggregation, achieving state-of-the-art quality.

DMesh: A novel differentiable mesh representation enabling efficient gradient-based optimization for diverse 3D shape applications.

DGNet enhances weakly supervised point cloud segmentation by aligning feature embeddings to a mixture of von Mises-Fisher distributions, achieving state-of-the-art performance.

DistillNeRF: a self-supervised learning framework enabling accurate 3D scene reconstruction from sparse, single-frame images by cleverly distilling features from offline NeRFs and 2D foundation models…

DisC-GS enhances Gaussian Splatting for real-time novel view synthesis by accurately rendering image discontinuities and boundaries, improving visual quality.

Director3D generates realistic 3D scenes and camera trajectories from text descriptions using a three-stage pipeline: Cinematographer, Decorator, and Detailer.

Direct3D: Revolutionizing image-to-3D generation with a scalable, native 3D diffusion model achieving state-of-the-art quality.

DiffusionBlend++ learns a 3D image prior via position-aware diffusion score blending, achieving state-of-the-art 3D CT reconstruction with superior efficiency.

DiffuBox refines 3D object detection using a novel diffusion-based approach, significantly improving accuracy across various domains by refining bounding boxes based on surrounding LiDAR point clouds.

Depth Anywhere enhances 360-degree monocular depth estimation by cleverly using perspective models to label unlabeled 360-degree data, significantly improving accuracy.

Depth Anything V2 drastically improves monocular depth estimation by using synthetic training data, scaling up the teacher model, and employing pseudo-labeled real images. It outperforms previous met…

DEL: Learns 3D particle dynamics from 2D images via physics-informed neural rendering, exceeding existing methods’ accuracy and robustness.

DeBaRA: a novel denoising-based model generates realistic & controllable 3D room layouts, surpassing existing methods.