3D Vision

GaussianMarker: A novel uncertainty-aware watermarking method ensures robust copyright protection for 3D Gaussian Splatting assets, invisibly embedding messages into model parameters and extractable …

GaussianCube revolutionizes 3D generative modeling with a structured, explicit radiance representation, achieving state-of-the-art results using significantly fewer parameters.

Gaussian Graph Network (GGN) revolutionizes novel view synthesis by efficiently generating generalizable Gaussian representations from multi-view images, achieving superior rendering quality with fewe…

Ex4DGS achieves real-time high-quality dynamic scene rendering using explicit 4D Gaussian representations and keyframe interpolation.

α-NeuS: A novel method for neural implicit surface reconstruction that accurately reconstructs both transparent and opaque objects simultaneously by leveraging the unique properties of distance fields…

Researchers developed a self-supervised learning framework to create high-dynamic-range 3D Gaussian Splatting (3DGS) models from noisy raw images, significantly improving reconstruction quality and sp…

ODIN, trained on a million 360° videos (360-1M), generates realistic novel views and reconstructs 3D scenes from single images.

FreeSplat achieves state-of-the-art novel view synthesis by accurately localizing 3D Gaussians from long image sequences, overcoming limitations of prior methods confined to narrow-range interpolation…

Flatten Anything Model (FAM) revolutionizes neural surface parameterization with unsupervised learning, handling complex topologies and unstructured data fully automatically.

OLIVINE uses visual foundation models for fine-grained image-to-LiDAR contrastive distillation, mitigating self-conflict issues and improving 3D representation learning.

FFAM uses feature factorization and gradient weighting to produce high-quality visual explanations for 3D object detectors, improving model interpretability and trust.

FewViewGS: A novel method for high-quality novel view synthesis from sparse images using a multi-stage training scheme and a new locality-preserving regularization for 3D Gaussians.

TRACKSTO4D: Fast & accurate 3D reconstruction from casual videos using 2D point tracks, drastically reducing runtime by up to 95% while matching state-of-the-art accuracy.

EVA: a novel method generates expressive 3D Gaussian human avatars from monocular RGB videos, excelling in detailed hand and facial expressions via context-aware density control and improved SMPL-X al…

Event-3DGS: First event-based 3D reconstruction using 3D Gaussian splatting, enabling high-quality, efficient, and robust 3D scene reconstruction in challenging real-world conditions.

DSPoser: A novel two-stage approach accurately estimates full-body pose from doubly sparse egocentric video data using masked autoencoders for temporal completion and conditional diffusion models for …

Era3D: High-resolution multiview diffusion using efficient row-wise attention, generates high-quality multiview images from single views, overcoming prior limitations.

eFreeSplat: a novel, epipolar-free 3D Gaussian splatting model for generalizable novel view synthesis, surpassing state-of-the-art methods by achieving superior geometry reconstruction and novel view …

EgoChoir: a novel framework harmonizes visual appearance, head motion, and 3D objects to accurately estimate 3D human contact and object affordance from egocentric videos, surpassing existing methods.

EfficientCAPER: A novel end-to-end framework achieves fast & robust category-level articulated object pose estimation by using a joint-centric approach, eliminating post-processing optimization and en…