analiza aiqbench
CubicSplat addresses the inherent instability in differentiable vector graphics by replacing discontinuous Bézier solvers with uniform polyline surrogates that guarantee bounded geometric error. This architectural shift resolves the "gradient seesaw" problem, yielding well-conditioned gradients and significantly faster training speeds without relying on auxiliary regularization heuristics. The method achieves state-of the-art reconstruction quality on standard benchmarks, advancing the practicality of optimizing parametric primitives for high-fidelity image generation.
CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation
arXiv:2608.20803v1 Announce Type: cross Abstract: Vector graphics are prized for their resolution independence, compact storage, and direct editability, making differentiable optimization of their parametric primitives an attractive goal. Yet classical rasterization is discontinuous with respect to geometry, and existing remedies that smooth the forward pass demand increasingly elaborate heuristics as scene complexity grows. We trace this fragility to a gradient seesaw: design choices that improve forward geometric exactness can systematically degrade the induced gradient signal, and vice versa. To navigate this tension we introduce CubicSplat, a differentiable vector rasterizer that replaces B\'ezier closest-point solvers with uniform polyline surrogates whose geometric error is bounded at $O(S^{-2})$. The resulting static computation graph yields well-conditioned gradients by construction, while a compositing-derived visibility mechanism prunes degenerate primitives without auxiliary regularization. On DIV2K and Kodak benchmarks CubicSplat achieves state-of-the-art reconstruction quality with over 2 dB PSNR gain in the closed-fill setting, while training up to 4x faster than prior methods. The code is available at https://github.com/CubicSplat/repo
Abstract:Vector graphics are prized for their resolution independence, compact storage, and direct editability, making differentiable optimization of their parametric primitives an attractive goal. Yet classical rasterization is discontinuous with respect to geometry, and existing remedies that smooth the forward pass demand increasingly elaborate heuristics as scene complexity grows. We trace this fragility to a gradient seesaw: design choices that improve forward geometric exactness can systematically degrade the induced gradient signal, and vice versa. To navigate this tension we introduce CubicSplat, a differentiable vector rasterizer that replaces Bézier closest-point solvers with uniform polyline surrogates whose geometric error is bounded at $O(S^{-2})$. The resulting static computation graph yields well-conditioned gradients by construction, while a compositing-derived visibility mechanism prunes degenerate primitives without auxiliary regularization. On DIV2K and Kodak benchmarks CubicSplat achieves state-of-the-art reconstruction quality with over 2 dB PSNR gain in the closed-fill setting, while training up to 4x faster than prior methods. The code is available at this https URL
27 pages, 8 figures, 7 tables. ECCV 2026 Oral
Graphics (cs.GR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2608.20803 [cs.GR]
(or arXiv:2608.20803v1 [cs.GR] for this version)
https://doi.org/10.48550/arXiv.2608.20803 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 269 cuvinte
Subiecte conexe
Performance Profiling on AMD GPUs – Part 5: Profiling-Driven Kernel Optimization with an AI Code-Assist Tool
AMD · 16 iul. 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · 4 sept. 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · 8 oct. 2026
On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
arXiv · 15 iun. 2026