Pith. sign in

REVIEW 34 cited by

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.10733 v8 pith:MQNZRO47 submitted 2024-10-14 cs.CV cs.AI

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

classification cs.CV cs.AI
keywords autoencodermodelscompressiondc-aediffusionhighhigh-resolutionspatial
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio (e.g., 8x), but fail to maintain satisfactory reconstruction accuracy for high spatial compression ratios (e.g., 64x). We address this challenge by introducing two key techniques: (1) Residual Autoencoding, where we design our models to learn residuals based on the space-to-channel transformed features to alleviate the optimization difficulty of high spatial-compression autoencoders; (2) Decoupled High-Resolution Adaptation, an efficient decoupled three-phases training strategy for mitigating the generalization penalty of high spatial-compression autoencoders. With these designs, we improve the autoencoder's spatial compression ratio up to 128 while maintaining the reconstruction quality. Applying our DC-AE to latent diffusion models, we achieve significant speedup without accuracy drop. For example, on ImageNet 512x512, our DC-AE provides 19.1x inference speedup and 17.9x training speedup on H100 GPU for UViT-H while achieving a better FID, compared with the widely used SD-VAE-f8 autoencoder. Our code is available at https://github.com/mit-han-lab/efficientvit.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 34 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Diffusing in the Right Space: A Systematic Study of Latent Diffusability

    cs.CV 2026-06 unverdicted novelty 7.0

    A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.

  2. Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space

    cs.CL 2026-05 unverdicted novelty 7.0

    The paper introduces Manta-LM, which approximates the Hamilton-Jacobi-Bellman optimal policy via Flow Matching in a rectified latent control space to enable high-fidelity parallel language generation.

  3. Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning

    cs.LG 2026-07 conditional novelty 6.0

    Clients encode private images through a frozen public autoencoder, compute additive class-conditional latent statistics protected by differential privacy, and the server decodes a synthetic dataset that trains competi...

  4. X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving

    cs.CV 2026-06 unverdicted novelty 6.0

    X-Mind proposes an efficient internal visual chain-of-thought using compressed BEV sketches and recurrent block diffusion to embed predictive world models into end-to-end driving policies.

  5. SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models

    cs.CV 2026-06 unverdicted novelty 6.0

    SPAR introduces semantic-pixel self-alignment via asymmetric tokenizer and adaptive routing for unified MLLMs that achieve SOTA generation and reconstruction while retaining understanding.

  6. Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs

    cs.CV 2026-06 unverdicted novelty 6.0

    A causal VAE with variable reference guidance and a Rectified Flow Transformer enables real-time streamable high-quality talking portrait video generation from audio and images.

  7. PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

    cs.CV 2026-05 unverdicted novelty 6.0

    PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claime...

  8. Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis

    cs.CV 2026-05 unverdicted novelty 6.0

    Spatial Gram Alignment aligns internal self-similarities of LDM features with foundation priors to reconcile global structure and fine details in ultra-high-resolution text-to-image synthesis.

  9. Rethinking Cross-Layer Information Routing in Diffusion Transformers

    cs.CV 2026-05 unverdicted novelty 6.0

    DAR replaces residual addition in DiTs with learnable, timestep-adaptive aggregation of sublayer outputs, yielding 2.11 FID improvement on SiT-XL/2 and 8.75x faster convergence on ImageNet 256x256.

  10. Rethinking Cross-Layer Information Routing in Diffusion Transformers

    cs.CV 2026-05 conditional novelty 6.0

    DAR replaces residual addition in DiTs with learnable timestep-adaptive non-incremental aggregation of sublayer outputs, improving FID by 2.11 on ImageNet 256x256 and accelerating convergence by 8.75x.

  11. LatentBox: Storing AI-Generated Images at Scale via a Latent-First Design

    cs.DC 2026-05 conditional novelty 6.0

    LatentBox is a latent-first storage system that stores compressed latents as durable objects with on-demand GPU reconstruction and dynamic image/latent caching, achieving 78.7% storage reduction with competitive laten...

  12. LatentBox: Storing AI-Generated Images at Scale via a Latent-First Design

    cs.DC 2026-05 unverdicted novelty 6.0

    LatentBox is a latent-first storage system that cuts persistent storage for AI images by 78.7% while keeping mean and tail latency competitive with traditional pixel storage.

  13. ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices

    cs.CV 2026-05 unverdicted novelty 6.0

    ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency p...

  14. Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space

    cs.CL 2026-05 unverdicted novelty 6.0

    Manta-LM approximates the HJB equation via flow matching in latent control space to realize closed-loop optimal control for language generation.

  15. Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space

    cs.CL 2026-05 unverdicted novelty 6.0

    Language generation is recast as optimal control and solved approximately with flow matching in rectified latent control space to enable high-fidelity parallel text generation.

  16. What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion

    cs.CV 2026-05 unverdicted novelty 6.0

    Prior-Aligned AutoEncoders shape latent manifolds with spatial coherence, local continuity, and global semantics to improve latent diffusion, achieving SOTA gFID 1.03 on ImageNet 256x256 with up to 13x faster convergence.

  17. MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality

    cs.CV 2026-05 unverdicted novelty 6.0

    MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.

  18. Latent-Compressed Variational Autoencoder for Video Diffusion Models

    cs.CV 2026-04 unverdicted novelty 6.0

    A frequency-based latent compression method for video VAEs yields higher reconstruction quality than channel-reduction baselines at fixed compression ratios.

  19. Gram-MMD: A Texture-Aware Metric for Image Realism Assessment

    cs.CV 2026-04 unverdicted novelty 6.0

    Gram-MMD is a texture-aware realism metric that computes MMD on upper-triangular Gram matrices from backbone activations, providing complementary information to semantic distributional metrics.

  20. MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model

    cs.CV 2026-03 unverdicted novelty 6.0

    MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.

  21. PixelGen: Improving Pixel Diffusion with Perceptual Supervision

    cs.CV 2026-02 accept novelty 6.0

    PixelGen augments pixel diffusion with gated perceptual supervision to reach FID 5.11 on ImageNet-256 and GenEval 0.79 in text-to-image, narrowing the gap to latent methods without VAEs.

  22. TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning

    cs.CV 2025-12 conditional novelty 6.0

    TinyHistory compresses long video history into a ~5k-token context via a two-stage learning scheme, achieving consistency on par with heavier baselines at lower memory cost.

  23. Native and Compact Structured Latents for 3D Generation

    cs.CV 2025-12 unverdicted novelty 6.0

    Introduces O-Voxel omni-voxel representation and Sparse Compression VAE for structured native 3D latents, enabling efficient training of large flow-matching models that produce higher-quality geometry and materials th...

  24. DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation

    cs.CV 2025-11 conditional novelty 6.0

    DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while clos...

  25. CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

    cs.CV 2025-03 unverdicted novelty 6.0

    CoT-VLA is a 7B VLA that generates future visual frames autoregressively as planning goals before actions, outperforming prior VLAs by 17% on real-world tasks and 6% in simulation.

  26. Long-Context Autoregressive Video Modeling with Next-Frame Prediction

    cs.CV 2025-03 unverdicted novelty 6.0

    FAR baseline plus asymmetric kernels for long short-term context modeling achieves SOTA short and long video generation in autoregressive setups.

  27. HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion

    cs.CV 2026-07 conditional novelty 5.5

    Training-free sparse attention for video DiTs cuts latency up to ~2.1× via 3D local-window clustering, hybrid step updates, and hardware-aware cluster merging while improving fidelity over prior sparse methods.

  28. Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation

    cs.CV 2026-07 conditional novelty 5.0

    A chunk-wise streaming video model with bounded multi-scale memory and streaming 4K upscaling reports real-time interactive long-form generation and top Arena preference/stability scores.

  29. SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models

    cs.CV 2026-06 unverdicted novelty 5.0

    SPAR introduces a semantic-pixel self-alignment tokenizer and dynamic token routing to create a unified multimodal model that performs both understanding and generation at claimed state-of-the-art levels.

  30. SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

    cs.CV 2026-05 unverdicted novelty 5.0

    SANA-WM is a 2.6B-parameter efficient world model that synthesizes minute-scale 720p videos with 6-DoF camera control, trained on 213K public clips in 15 days on 64 H100s and runnable on single GPUs at 36x higher thro...

  31. Video Generation with Predictive Latents

    cs.CV 2026-05 unverdicted novelty 5.0

    PV-VAE improves video latent spaces for generation by unifying reconstruction with future-frame prediction, reporting 52% faster convergence and 34.42 FVD gain over Wan2.2 VAE on UCF101.

  32. Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation

    cs.CV 2026-04 unverdicted novelty 5.0

    Asset Harvester converts sparse in-the-wild object observations from AV driving logs into complete simulation-ready 3D assets via data curation, geometry-aware preprocessing, and a SparseViewDiT model that couples spa...

  33. Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models

    cs.LG 2025-10 unverdicted novelty 5.0

    GRWM uses temporal contrastive learning to geometrically regularize latent spaces in world models for high-fidelity cloning of deterministic 3D worlds.

  34. Seedance 1.0: Exploring the Boundaries of Video Generation Models

    cs.CV 2025-06 unverdicted novelty 4.0

    Seedance 1.0 generates 5-second 1080p videos in about 41 seconds with claimed superior motion quality, prompt adherence, and multi-shot consistency compared to prior models.