Reinforcement learning from human feedback (RLHF) for 3D generation is now established across a number of works, but most existing pipelines optimise explicit surface representations, often by converting radiance fields into meshes and training heavily on surface-supervised data. We instead fine-tune a pretrained 3D-aware generative model directly from a learned reward over radiance-field density ($σ$) values, with no externally supplied mesh or shape prior.
arXiv:2609.07137v1 Announce Type: cross Abstract: Recent image-to-3D generation models built on flow-matching diffusion Transformers (DiT) can produce high-fidelity meshes, yet their post-training st...
The paper introduces Dynamic Homing Optimization (DHO), a forward‑process reinforcement learning approach that reinterprets negative‑trajectory optimization as attraction toward positive samples. DHO uses Minimum‑Cost Attractive Matching to assign each negative sample a distinct positive target and Time‑Aware Dynamic Correction to guide trajectories toward those targets. Building on DHO, the authors present Flow3D‑Pro, an image‑to‑3D geometry generation framework that outperforms existing DPO, GRPO, and NFT‑style objectives and produces higher‑quality 3D meshes.
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.
arXiv:2607. 05568v1 Announce Type: cross Abstract: Representing 3D shapes as compact sets of geometric primitives is fundamental to robotics, simulation, and scene understanding.
arXiv:2607.05568v2 Announce Type: replace-cross Abstract: Compact primitive abstractions represent 3D shapes with a few geometric primitives while preserving recognizable components. Learned methods...
AGORA is a new framework that extends 3D Gaussian Splatting with a generative adversarial network to produce high‑fidelity, animatable 3D head avatars. It introduces a lightweight FLAME‑conditioned deformation branch that predicts per‑Gaussian residuals for identity‑preserving, fine‑grained expression control, and a dual‑discriminator training scheme that enforces expression fidelity. The system achieves real‑time inference at 250 FPS on a single GPU and, for the first time, CPU‑only animatable 3DGS avatar synthesis at ~9 FPS.
arXiv:2606. 19162v1 Announce Type: new Abstract: Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent object structure that matching-based training is intended to learn from the data itself.
Optimizing 3D shapes within the latent spaces of deep generative models is fundamental to computer assisted engineering, yet remains prone to a critical failure mode we term manifold drift: the tendency of gradient-based optimization to move latent vectors away from the manifold of valid shapes. This problem is exacerbated in state-of-the-art 3D shape generative models that operate in increasingly high-dimensional latent spaces where valid shapes occupy a vanishingly small fraction of the full space.
arXiv:2608.23410v1 Announce Type: new Abstract: Photorealistic novel view synthesis of people remains challenging at high spatial resolutions and across multiple target cameras, where preserving iden...
Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models operate purely in a feed-forward, deterministic regime, \ie~they cannot generate plausible geometry beyond what the input views directly support.
arXiv:2603. 04976v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored.
arXiv:2607. 00885v1 Announce Type: cross Abstract: Recent advances in neural rendering have established 3D Gaussian Splatting (3DGS) as a highly efficient representation for novel view synthesis, enabling fast training and real-time rendering with strong fidelity.