First implementation of a 3D Gaussian renderer on an Intelligence Processing Unit (IPU) with 1,472 independent tiles using only on-chip SRAM.

This paper proposes methods for intrinsic decomposition of radiance fields using Gaussian splatting, enabling adaptive modeling, disentanglement, and editing of textures in images.

VEDAL introduces a variational, error-driven asynchronous learning framework to efficiently prune 3D Gaussian Splatting, achieving high compression ratios with minimal loss in novel view synthesis qua…

The paper proposes a novel method to improve the simultaneous representation of appearance and geometry in 3D Gaussian Splatting by introducing an additional geometry opacity parameter.

This paper introduces Deformable Triangle Splatting, a method for representing non-convex shapes in radiance fields using triangles with learnable control points, enabling differentiable rendering.

The paper proposes a fast and lightweight novel view synthesis method using a differentiable Multiplane Image (MPI) representation, achieving significant speed and size improvements over state-of-the-…

The paper presents GrainGS, a dynamic Gaussian framework for scene reconstruction that balances fine-grained motion modeling, structural stability, and compact representation.

The paper proposes PointSplat, a human-centric approach for producing compact 3D human representations from input views, reducing inter-view redundancy and improving rendering quality.

The paper presents Odin, a distributed training system for point-based neural rendering (PBNR) that replaces global barriers with primitive-level synchronization, improving throughput and hiding criti…

City-Mesh3R is a scalable, end-to-end framework that reconstructs high-fidelity, watertight 3D surface meshes of entire city-scale environments directly from large collections of multi-view images.

GLAM-SLAM is a real-time, decoupled Gaussian-splatting SLAM system for large-scale outdoor scenes with a robust feature-based frontend and structured sparse mapping representation.

This paper introduces a nonlinear, actuator-aware safety filter for 3D Gaussian Splatting (3DGS) based on full quadrotor dynamics, reducing trajectory jerk by 47% and running 2.25 times faster than ex…

This paper proposes Wat3R, a cross-domain semi-supervised learning framework for adapting 3D reconstruction models from air to underwater scenes using unlabeled real underwater video footage and a tea…

This paper introduces FutureSurf, a benchmark and dataset for evaluating dynamic-scene reconstruction methods' ability to predict future surface geometry.

PatchPoison introduces a lightweight dataset-poisoning method that injects small, high-frequency adversarial patches into multi-view image datasets to systematically corrupt feature matching and degra…