ZipTok3D is a 3D tokenizer that achieves high‑fidelity reconstruction from extremely short token sequences by organizing object geometry into progressively informative global‑token prefixes. During training, nested dropout truncates the latent sequence, forcing each retained prefix to reconstruct the full object, which prioritizes essential geometric information in the leading tokens. The decoder uses a parameter‑shared Transformer block to iteratively recover fine‑grained geometry, enabling reconstruction quality comparable to a 32‑token baseline while using only one token on ShapeNet and four on TRELLIS.
arXiv:2608. 01185v1 Announce Type: cross Abstract: Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering.
KISS-GS is a modular compression pipeline for 3D Gaussian Splatting (3DGS) scenes that separates compression from training. It first compacts a vanilla 3DGS scene by 15.7× using state‑of‑the‑art pruning, then encodes the result into the SOG‑XT image‑based format, achieving an additional 6.6× reduction. Optional encoding‑aware fine‑tuning can further cut the size by 2.2×, yielding total reductions of 85× to 319× on standard benchmarks while enabling web‑native decoding.
arXiv:2608. 04515v1 Announce Type: cross Abstract: Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices.
arXiv:2608. 19567v1 Announce Type: new Abstract: While text-to-3D generation has advanced rapidly, achieving high geometric fidelity at low inference cost remains challenging.
3D vision-language models (3D VLMs) enable spatial reasoning over multi-view scenes but suffer from substantial token redundancy due to duplicated observations and large uninformative regions, leading to high computational cost. Although visual token compression has shown promise in accelerating 2D VLMs, it fails to capture the structured nature of 3D scenes and leads to incomplete spatial coverage and loss of fine-grained details.
RecGen3D is a framework that merges feed‑forward reconstruction and diffusion‑based generation to address the trade‑off between reconstruction fidelity and generative plausibility in sparse‑view 3D modeling. By aligning both models in a shared canonical space and using decoupled cooperative learning, the system stabilizes training and allows the reconstruction module to supply canonical geometric anchors while the diffusion generator refines and completes the structure. Experiments show that RecGen3D outperforms existing methods in producing complete and consistent 3D models from sparse observations.
In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.
The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. By representing only occupied voxels in a compact latent space and training a masked autoregressive transformer with photometric supervision via differentiable 3D Gaussian Splatting, the method predicts missing latent tokens and spatial support, enabling efficient and spatially consistent generation of unseen regions. Experiments on synthetic indoor scenes and RealEstate10k demonstrate higher novel‑view quality and real‑world applicability compared to prior work.
Point Diffusion Mamba (PDM) is a new method that fuses diffusion models with state‑space modeling to perform single‑view 3D reconstruction when training data are scarce. It uses a lightweight reconstruction module for unordered point‑clouds, a Local Geometric Aggregation module combined with Mamba blocks to capture both global geometry and local detail, and a Hierarchical Feature Integration Network to merge high‑level semantic and local geometric features for each point. A Dynamic Weighted Sampling strategy further improves reconstruction quality by integrating generative priors, and experiments on ShapeNet and Pix3D show that PDM outperforms existing state‑of‑the‑art approaches.
arXiv:2608.24293v1 Announce Type: new Abstract: Latent diffusion models have emerged as a dominant framework for high-fidelity image and video synthesis, operating in compact latent spaces with varia...
arXiv:2605.29655v4 Announce Type: replace Abstract: Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D t...
arXiv:2606.06158v2 Announce Type: replace Abstract: Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous...