Searcharxiv⌕ Search

arXiv subjects

Gordon Wetzstein

Publications and source records attributed to Gordon Wetzstein.

At least 19 recordsLinked to original sources

Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers

Latent diffusion models rely on a decoder to map denoised latents to pixels, adding complexity and inference cost. We introduce Decoding Without a Decoder (DWD), which lets a finetuned diffusion transformer produce final pixels directly through a linear head. Unlike previous methods, where the denoising output leads to final pixels, DWD separates the two roles: the original denoising head continues to drive sampling, then the new DWD head predicts the pixels at the final step. We extend pretrained latent models with DWD efficiently by finetuning only the last few transformer blocks, training the DWD head with pixel quality losses while anchoring the denoising head to the pretrained model to preserve the sample trajectory. Across latent image and video generators, DWD removes the decoder and reduces inference cost while maintaining or even improving pixel quality. On Wan video generation, it visibly reduces detail distortion and flickering, lowering warping error by 23%. Remarkably, the same separation also improves pixel diffusion models that do not even use a decoder: a final-step DWD head produces substantially better texture detail in text-to-image generation, and improves ImageNet FID from 1.55 to 1.43, a new state of the art among pixel flow models.

cs.CV↗

Learning Anisotropic Prediction Targets for Flow Models

Flow-based generative models are trained on a hand-chosen prediction target, such as the velocity, the noise, or the clean data. This choice strongly affects training and sample quality. We introduce Anisotropic Flow Models (AnisoFlow), which replaces a fixed prediction target with a fully learnable one. AnisoFlow learns to scale the noise component of the target anisotropically, assigning a separate nonnegative weight to each direction in a jointly learned basis. A closed-form map recovers the velocity from the network's prediction, leaving the architecture, flow-matching loss, and sampler unchanged. Since recovery is exact, training optimizes the target purely to make it easier for the network to predict. We theoretically analyze the resulting prediction error and predict that the preferred noise weight in each direction scales near-linearly with data variance, in agreement with the weights learned empirically in pixel space. AnisoFlow improves FID from 1.90 to 1.55 over the JiT baseline on ImageNet 256$\times$256, by learning only the prediction target, without representation alignment or architectural changes. In pixel-space text-to-image generation, AnisoFlow improves image quality and, through better-conditioned velocity recovery, largely removes patch-seam artifacts under reduced-precision inference.

cs.CV↗

Same Physics, Different Gradients: A State-of-the-Art Report on Differentiable Physics Simulation

Differentiable simulation propagates derivatives through a physics simulator, turning animation, system identification, control, and computational design into gradient-based optimization. Engines differ in the physics they model and, less visibly, in which mathematical object they differentiate. We separate two questions the literature conflates. The referent is which object the returned derivative belongs to: the finite computation that executed, the converged equation it approximates, or the continuous dynamics. The realization describes the organization of the backward pass: automatically generated differentiation, an equation-level adjoint solve, or a custom adjoint. The referent defines the target against which exactness is assessed; the implementation determines how accurately that target is approximated. Cost depends on the realization together with how the states needed by the backward pass are retained or recovered. Crossing the axes places every method and engine we classify in a cell, separates claims the literature merges, and shows that the apparent trade-off between exactness and memory follows from how methods have been built rather than from a constraint. A second, orthogonal taxonomy covers contact, where the map is non-smooth. We then ask whether a correct gradient helps. Four mechanisms by which useful gradients are lost are cataloged and measured on one testbed, where the advantage of the exact derivative over the equation-level adjoint depends on where the fitting target comes from as much as on the solver budget, and we review the evidence that zeroth-order methods can outperform simulator gradients in the regimes where those mechanisms act. The model classes, systems techniques and applications are surveyed through this lens, and we close with a reporting checklist, a released diagnostic that computes it, and a research agenda.

cs.GR↗

SoftPAT3D: Physics-Augmented Text-to-3D Scene Generation with Deformables

We present SoftPAT3D, a physics-augmented framework for text-to-3D scene generation in which deformable objects, such as cloth, stuffed toys and ropes, are generated as physically valid, simulation-ready bodies and placed in intersection-free contact with the furniture that supports them, with one another and with themselves. Existing physics-augmented pipelines simulate rigid bodies only and cannot accommodate a generated deformable object, which text-to-3D generation returns as a geometrically invalid mesh, sometimes self-intersecting, that has no rest shape, no material model and no admissible initial state. These are the inputs a deformable simulation requires, and we construct each from information already in the pipeline. The rest shape comes from how the object is manufactured rather than from the generated physically inconsistent deformed configuration, and a material library assigns each deformable object its initial elastic parameters, which can then be optimized. The occluded support is regenerated and converted into a watertight collision mesh, each object is released from an optimizable placement above the supporting part that the prompt specifies, and the complete scene is driven to static equilibrium under one unified contact model, with completion verified by geometric checks and a vision-language model. When a scene fails the prompt, a grid search over placements corrects it, and the adjoint of a differentiable simulation of the same contact energy reaches the targets the grid does not, places several bodies jointly and recovers and optimizes material parameters. Multi-body scenes equilibrate in a single simulation, and the pipeline also runs from the text prompt alone. On all sixty-five prompts, SoftPAT3D produces no undesired interpenetration of any kind, whereas every other system does, and its scenes directly support scene editing and robotic manipulation.

cs.CV↗

Asymmetric Flow Models

Flow-based generation in high-dimensional pixel spaces is difficult because velocity prediction requires modeling high-dimensional noise, even when data has strong low-rank structure. We present Asymmetric Flow Modeling (AsymFlow), a rank-asymmetric velocity parameterization that restricts noise prediction to a low-rank subspace while keeping data prediction full-dimensional. From this asymmetric prediction, AsymFlow analytically recovers the full-dimensional velocity, leaving the network architecture and the standard flow-matching training and sampling procedures unchanged. On ImageNet 256$\times$256, AsymFlow achieves a leading 1.57 FID, outperforming prior DiT/JiT-like pixel diffusion models by a large margin. AsymFlow also provides the first-ever route for finetuning pretrained latent flow models into pixel-space models: aligning the low-rank pixel subspace to the latent space gives a seamless initialization that preserves the latent model's high-level semantics and structure, so finetuning mainly improves low-level mismatches rather than relearning pixel generation. We show that the pixel AsymFlow model finetuned from FLUX.2 klein 9B establishes a new state of the art for pixel-space text-to-image generation, beating its latent base on HPSv3, DPG-Bench, and GenEval while qualitatively showing substantially improved visual realism.

cs.CV↗

WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform

World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applications, and simulator-based evaluation, making them insufficient for assessing increasingly comprehensive world models. In this work, we introduce WorldArena 2.0, an expanded benchmark that systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform. Along the modality dimension, WorldArena 2.0 extends evaluation from vision-only to visuotactile modalities, enabling assessment of multimodal perception and prediction. Along the functionality dimension, it extends beyond policy evaluation and planning to assess world models as interactive RL environments for policy optimization. Along the platform dimension, it moves beyond simulator-only evaluation to a diverse suite of simulated and real-world robotic settings across multiple embodiments. Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance, providing a comprehensive testbed for tracking progress toward embodied world models. The project page including codes and demos is available at: https://world-arena.ai/.

cs.RO↗

World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video

We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos. Our approach conditions a video model on dense, pixel-aligned renderings that encode appearance, geometry, and 3D scene motion along both input and target camera trajectories to correct rendering artifacts and fill in missing regions from an initial reconstruction. To train this model, we construct a dataset of aligned multiview video pairs and dynamic 3DGS representations, with simulated artifacts characteristic of monocular reconstruction. At test time, we distill the model's generations, including newly observed regions and motions, back into a single consistent, high-quality dynamic 3DGS, improving both novel-view synthesis and the underlying 3D motion. Our method sets a new state of the art in 4D reconstruction and seamlessly generalizes to in-the-wild videos with large viewpoint changes and dynamic motions.

cs.CV↗

FluidGen: Physics-Aware Fluid Video Generation via Motion-Guided Post-Training

Video generation models produce visually compelling motion but systematically fail on fluid phenomena, including smoke, fire, and explosion debris, where outputs lack coherent vortical structure and collapse to bland dynamics that violate the physics of real fluids. Classical solvers achieve high physical fidelity but require detailed 3D scenes and carefully tuned parameters, making them impractical for in-the-wild imagery and video generation. We address this gap by injecting a data-driven fluid prior into a pre-trained video model, trained on a mixture of high-fidelity Houdini simulation data with paired velocity-field ground truth and curated in-the-wild fluid video data for appearance diversity. The core of our approach is a dual stream architecture that predicts per-frame velocity fields alongside RGB, supervised by simulation ground truth. This auxiliary signal regularizes generation toward physically consistent motion and exposes an interpretable physical quantity that we further leverage as a reward for velocity-aware direct preference optimization. Our model produces substantially more realistic fluid dynamics sequences than strong video baselines and optimization-based methods. Project page: https://y-zheng18.github.io/FluidGen/

cs.CV↗

Generative Representation Learning for Scalable Latent Tokenization

We introduce an approach for self-supervised representation learning designed to be used as a tokenizer for generative modeling. Our objective supervises a representation loss by factorizing the pointwise mutual information of the data, which we estimate by taking information differences between conditional predictions from a learned generative model. We justify our algorithm theoretically and empirically, demonstrating that our generative approach to representation learning avoids dimensional collapse and feature suppression in cases where commonly used methods like DINO and LeJEPA fail. Moreover, we show our representation learning technique is scalable; expending more compute leads to predictably better latent tokenization. For the first time, we perform a careful analysis of the combined flop efficiency of tokenizer and generative model and demonstrate that our approach is a compute-optimal improvement over direct diffusion for pixel-space generation, obtaining an FID-50K of 2.18 with JiT-L. Applied to ImageNet and the text-to-image dataset GPIC, we show tokenizer encoder scaling laws for diffusability, where extrapolating our approach achieves representations in 7x fewer FLOPs than DINOv2 on ImageNet and 8x fewer FLOPs than WebSSL on GPIC.

cs.LG↗

PCAsplat: Gaussian Splatting with Local PCA Regularization

Gaussian splatting has emerged as a flexible representation for 3D reconstruction from posed images. However, existing methods are optimized primarily using rasterization-based losses, which supervise a splat only when it contributes to sampled camera rays. Gaussians that are occluded or contribute little to the sampled view therefore receive weak or no geometric gradients and may drift away from the underlying surface, producing undesired floaters. We introduce PCAsplat, a geometry-aware regularization framework for Gaussian splatting based on differentiable local principal component analysis (PCA). Our PCA regularizer acts directly on neighborhoods of Gaussian centers and can therefore update Gaussians that do not contribute to the current training view. We regularize the PCA eigenvalues to encourage Gaussians to move to the underlying surface with isotropic tangent-plane coverage. We also align each Gaussian normal with the PCA-estimated neighborhood normal to enforce consistent orientation. Experiments on DTU, Tanks and Temples, and NeRF Synthetic show that the splats produced by PCAsplat better approximate samples of the reference surface while substantially reducing undesired floaters. These surface-aligned splats enable downstream geometry-processing tasks, including point cloud segmentation, and direct Poisson reconstruction. Additionally, PCAsplat remains competitive under conventional novel view synthesis and mesh extraction tasks. Code will be released.

cs.CV↗

Level-of-Token Diffusion

Image and video diffusion models allocate equal computation to every region, even when the intended scene calls for varying levels of detail. The spatial distribution of detail can often be anticipated before generation, indicating where computation can be reduced. We introduce Level-of-Token (LoT) Diffusion, a framework that turns this knowledge into an explicit multiresolution token layout (Level-of-Token layout) for adaptive and efficient generation. Tokens represent rectangular patches of varying sizes and shapes, allocating finer tokens where detail is needed and coarser tokens elsewhere. We adapt pretrained diffusion transformers to LoT layouts through a patch-wise asymmetric flow parametrization and embeddings for multiresolution tokens, preserving full-resolution flow prediction at every denoising step while processing only a reduced token sequence. LoT Diffusion enables layout-adaptive generation while preserving pretrained generative priors. We demonstrate LoT with layouts derived from semantic masks, bounding boxes, texture variance, and depth-of-field cues, as well as agentic plans. Across image and video generation, LoT offers favorable quality-efficiency tradeoffs, with significant speedups determined by the layout's token budget. Our project website is at https://georgenakayama.github.io/lotdiffusion/.

cs.CV↗

Mode Seeking meets Mean Seeking for Fast Long Video Generation

Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training paradigm where Mode Seeking meets Mean Seeking, decoupling local fidelity from long-term coherence based on a unified representation via a Decoupled Diffusion Transformer. Our approach utilizes a global Flow Matching head trained via supervised learning on long videos to capture narrative structure, while simultaneously employing a local Distribution Matching head that aligns sliding windows to a frozen short-video teacher via a mode-seeking reverse-KL divergence. This strategy enables the synthesis of minute-scale videos that learns long-range coherence and motions from limited long videos via supervised flow matching, while inheriting local realism by aligning every sliding-window segment of the student to a frozen short-video teacher, resulting in a few-step fast long video generator. Evaluations show that our method effectively closes the fidelity-horizon gap by jointly improving local sharpness, motion and long-range consistency. Project website: https://primecai.github.io/mmm/.

cs.CV↗

BulletTime: Decoupled Control of Time and Camera Pose for Video Generation

Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and temporal control. We introduce a 4D-controllable video diffusion framework that explicitly decouples scene dynamics from camera pose, enabling fine-grained manipulation of both scene dynamics and camera viewpoint. Our framework takes continuous world-time sequences and camera trajectories as conditioning inputs, injecting them into the video diffusion model through a 4D positional encoding in the attention layer and adaptive normalizations for feature modulation. To train this model, we curate a unique dataset in which temporal and camera variations are independently parameterized; this dataset will be made public. Experiments show that our model achieves robust real-world 4D control across diverse timing patterns and camera trajectories, while preserving high generation quality and outperforming prior work in controllability. See our website for codes and video results: https://19reborn.github.io/Bullet4D/

cs.CV↗

Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control

Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or keyboard input, limiting their utility for embodied interaction. We introduce a human-centric video world model that is conditioned on both tracked head pose and joint-level hand poses. For this purpose, we evaluate existing diffusion transformer conditioning strategies and propose an effective mechanism for 3D head and hand control, enabling dexterous hand--object interactions. We train a bidirectional video diffusion model teacher using this strategy and distill it into a causal, interactive system that generates egocentric virtual environments. We evaluate this generated reality system with human subjects and demonstrate improved task performance as well as a significantly higher level of perceived amount of control over the performed actions compared with relevant baselines.

cs.CV↗

MeshFlow: Mesh Generation with Equivariant Flow Matching

Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important symmetries, including permutation invariance of faces and vertices. MeshFlow learns to generate triangle meshes directly as triangle soups, avoiding the need to serialize meshes into long autoregressive sequences. We adopt equivariant optimal-transport flow matching models that respect the key symmetries of triangle soups: arbitrary permutations of faces and permutations of the vertices within each face. Toward this goal, we propose a simple yet effective modification to the Diffusion Transformer architecture, resulting in a scalable network capable of modeling a velocity field while maintaining the desired equivariance. We further introduce an optimal-transport-based training objective that improves convergence by eliminating supervision signals that violate these symmetries. MeshFlow achieves mesh quality comparable to state-of-the-art autoregressive mesh generators while providing about an 18$\times$ speedup during inference. Project page is at https://qiisun.github.io/MeshFlow/.

cs.GR↗

Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis

Modern vehicle platforms are equipped with a rich sensor suite, including LiDAR, calibrated multi-camera rigs, and accurate ego-motion, that in principle offers strong signal for re-rendering a driving scene from novel viewpoints. A growing line of recent work leverages video diffusion models for this task, using their generative priors to synthesize plausible novel views from sparse vehicle observations. In practice, however, existing methods exploit only a fragment of this signal, and their quality tends to degrade as the target trajectory departs from the recorded driving path. We argue that this is fundamentally a multi-sensor fusion problem: sparse LiDAR reprojections supply accurate but incomplete metric geometry, surround-view reference imagery supplies dense appearance but no metric depth, and camera poses tie the two together across views. We introduce StreetNVS, a video diffusion framework that jointly conditions on all three signals through a Reference-Enhanced Camera Attention module based on a relative ray-level positional encoding. We develop a two-stage curriculum training strategy that gradually exposes the model to increasingly sparse LiDAR. On the Waymo Open Dataset, StreetNVS substantially outperforms state-of-the-art baselines under sparse LiDAR conditioning, matches methods that rely on 10-100 times denser point clouds. We further show capabilities of synthesizing coherent videos along extreme out-of-trajectory paths such as elevation, lane-shift, pullback, and rotation. Our website: https://streetnvs.github.io

cs.CV↗

Spectral Progressive Diffusion for Efficient Image and Video Generation

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natural opportunity for efficient generation, as high-resolution computation on noise-dominated frequencies is largely redundant. We propose Spectral Progressive Diffusion, a general framework that progressively grows resolution along the denoising trajectory of pretrained diffusion models. To this end, we develop a spectral noise expansion mechanism and derive an optimal resolution schedule from the model's power spectrum. Our framework supports training-free acceleration and a novel fine-tuning recipe that further improves efficiency and quality. We demonstrate significant speedups on state-of-the-art pretrained image and video generation models while preserving visual quality.

cs.CV↗

Fast Wave-optics Rendering of Multiplane Images for 3D Holographic Displays

Recent advances in neural rendering have unlocked unprecedented capabilities in 3D reconstruction and novel view synthesis, giving rise to applications such as virtual fly-throughs of a 3D scene reconstructed from a set of sparse, casually captured images. However, these renderings are viewed on a computer screen or conventional VR headsets as 2D images, greatly limiting the perceptual realism and immersiveness of such experiences. The rapid development in novel 3D scene representations calls for dedicated rendering algorithms that convert these readily-available 3D contents into formats that are compatible with emerging 3D display technologies, such as holographic displays. In this paper, we propose a wave-optics rendering pipeline that works with multiplane images (MPIs) for efficient and high-quality hologram synthesis. Our MPI-based computer-generated holography algorithm greatly outperforms state-of-the-art primitive-based CGH algorithms in terms of runtime, achieving speedups up to 250,000x while achieving comparable image quality, and significantly outperforms conventional layer-based CGH algorithms in terms of image quality. We validate our method extensively on a wide variety of 3D scene datasets both in simulation and through experimentally captured results, showing exceptional 3D focal stack and 4D light field reconstruction performance without sacrificing efficiency.

cs.GR↗