arXiv:2609.37775v1 Announce Type: cross Abstract: Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. M...
arXiv:2501. 09876v3 Announce Type: replace-cross Abstract: Generative modeling aims to generate new data samples that resemble a given dataset.
The paper introduces the Geometry‑Native Autoencoder (GAE), a compact latent space that can be decoded into appearance, depth, camera parameters, and point maps, enabling 3D‑consistent world generation. By reparameterizing a geometry foundation model’s features, GAE replaces traditional appearance‑centric latents and improves visual quality and 3D coherence, achieving significant reductions in FVD and camera‑trajectory error on benchmark datasets. The work demonstrates that a geometry‑native latent space can serve as a shared interface between perception and generation models.
4D generation synthesizes dynamic 3D scenes from conditions such as text or images. Existing methods either reconstruct generated RGB videos with a separate 4D model or adapt a particular video generator to predict geometry directly.
arXiv:2508.15774v2 Announce Type: replace Abstract: Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data...
The paper investigates how fine‑tuning pretrained visual encoders for faithful image reconstruction affects diffusion models that operate in the resulting latent space. It finds that such fine‑tuning reduces the effective dimensionality of the latent representation, causing standard velocity‑prediction flow‑matching to fit noise outside the low‑dimensional signal manifold and making optimization inefficient. Consequently, the authors propose using a clean‑data ($oldsymbol{x}_{0}$) parameterization, which focuses learning on the signal manifold and consistently improves text‑to‑image generation across multiple strong‑reconstruction encoders.
LF-MultiDiffusion is a training‑free method for generating spherical panoramas that extends MultiDiffusion by adding linear projections between target and reference image spaces. It reformulates latent aggregation as a regularized least‑squares problem and solves it with a Krylov‑based iterative solver during denoising, enabling denser and more natural mappings. The approach reduces the number of generator evaluations, improves inference speed by 15.36×, and yields better visual quality, text alignment, and panoramic consistency compared to the strongest training‑free baseline.
arXiv:2609.31620v1 Announce Type: new Abstract: Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual r...
arXiv:2605.12957v2 Announce Type: replace Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff be...
arXiv:2609.23182v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting now reconstructs renderable scenes from unposed, uncalibrated images. Yet, most models supervise only photometric co...
The paper introduces a compact neural appearance model for 3D Gaussian Splatting that replaces traditional low‑order spherical harmonics (SH) with a tiny shared MLP decoding per‑primitive latent codes. It compares SH with recent spherical appearance models, integrating all into a unified CUDA rasterizer and WebGL viewer, and demonstrates that the new neural representation reduces per‑primitive appearance storage from 192 to 28 bytes, speeds optimization by 1.3×, and improves reconstruction quality. The study also analyzes how different appearance parametrizations affect geometry recovery and the handling of non‑static scene content.