Flexible Techniques for Differentiable Rendering with 3D Gaussians
원문 초록
Fast, reliable shape reconstruction is an essential ingredient in many computer vision applications. Neural Radiance Fields demonstrated that photorealistic novel view synthesis is within reach, but was gated by performance requirements for fast reconstruction of real scenes and objects. Several recent approaches have built on alternative shape representations, in particular, 3D Gaussians. We develop extensions to these renderers, such as integrating differentiable optical flow, exporting watertight meshes and rendering per-ray normals. Additionally, we show how two of the recent methods are interoperable with each other. These reconstructions are quick, robust, and easily performed on GPU or CPU. For code and visual examples, see https://leonidk.github.io/fmb-plus
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MathOptAI.jl: Embed trained machine learning predictors into JuMP models
MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
ConsumerBench: Benchmarking Generative AI Applications on End-User Devices
TextureSplat: Per-Primitive Texture Mapping for Reflective Gaussian Splatting
Versatile and Fast Location-Based Private Information Retrieval with Fully Homomorphic Encryption over the Torus
SecONNds: Secure Outsourced Neural Network Inference on ImageNet
토론
이 논문과 연결된 포럼 글이 아직 없습니다.