Ji Hou

Chenfeng Xu, Bichen Wu, Ji Hou et al.

We present NeRF-Det, a novel method for indoor 3D detection with posed RGB images as input. Unlike existing indoor 3D detection methods that struggle to model scene geometry, our method makes novel use of NeRF in an end-to-end manner to explicitly estimate 3D geometry, thereby improving 3D detection performance. Specifically, to avoid the significant extra latency associated with per-scene optimization of NeRF, we introduce sufficient geometry priors to enhance the generalizability of NeRF-MLP. Furthermore, we subtly connect the detection and NeRF branches through a shared MLP, enabling an efficient adaptation of NeRF to detection and yielding geometry-aware volumetric representations for 3D detection. Our method outperforms state-of-the-arts by 3.9 mAP and 3.1 mAP on the ScanNet and ARKITScenes benchmarks, respectively. We provide extensive analysis to shed light on how NeRF-Det works. As a result of our joint-training design, NeRF-Det is able to generalize well to unseen scenes for object detection, view synthesis, and depth estimation tasks without requiring per-scene optimization. Code is available at \url{https://github.com/facebookresearch/NeRF-Det}.

Xiaoliang Dai, Ji Hou, Chih-Yao Ma et al. · meta-ai

Training text-to-image models with web scale image-text pairs enables the generation of a wide range of visual concepts from text. However, these pre-trained models often face challenges when it comes to generating highly aesthetic images. This creates the need for aesthetic alignment post pre-training. In this paper, we propose quality-tuning to effectively guide a pre-trained model to exclusively generate highly visually appealing images, while maintaining generality across visual concepts. Our key insight is that supervised fine-tuning with a set of surprisingly small but extremely visually appealing images can significantly improve the generation quality. We pre-train a latent diffusion model on $1.1$ billion image-text pairs and fine-tune it with only a few thousand carefully selected high-quality images. The resulting model, Emu, achieves a win rate of $82.9\%$ compared with its pre-trained only counterpart. Compared to the state-of-the-art SDXLv1.0, Emu is preferred $68.4\%$ and $71.3\%$ of the time on visual appeal on the standard PartiPrompts and our Open User Input benchmark based on the real-world usage of text-to-image models. In addition, we show that quality-tuning is a generic approach that is also effective for other architectures, including pixel diffusion and masked generative transformer models.

Yu-Jhe Li, Tao Xu, Ji Hou et al. · cmu

We tackle the task of text-to-3D creation with pre-trained latent-based NeRFs (NeRFs that generate 3D objects given input latent code). Recent works such as DreamFusion and Magic3D have shown great success in generating 3D content using NeRFs and text prompts, but the current approach of optimizing a NeRF for every text prompt is 1) extremely time-consuming and 2) often leads to low-resolution outputs. To address these challenges, we propose a novel method named 3D-CLFusion which leverages the pre-trained latent-based NeRFs and performs fast 3D content creation in less than a minute. In particular, we introduce a latent diffusion prior network for learning the w latent from the input CLIP text/image embeddings. This pipeline allows us to produce the w latent without further optimization during inference and the pre-trained NeRF is able to perform multi-view high-resolution 3D synthesis based on the latent. We note that the novelty of our model lies in that we introduce contrastive learning during training the diffusion prior which enables the generation of the valid view-invariant latent code. We demonstrate through experiments the effectiveness of our proposed view-invariant diffusion process for fast text-to-3D creation, e.g., 100 times faster than DreamFusion. We note that our model is able to serve as the role of a plug-and-play tool for text-to-3D with pre-trained NeRFs.

Jiaqi Zhang, Ji Hou, Qing Sun et al.

Estimating hip muscle forces and joint moments during gait typically relies on musculoskeletal simulation, which is informative but time-consuming and difficult to apply in clinical settings. This study developed a deep learning framework to predict these hip dynamics parameters directly from lower-limb gait kinematics and compared three representative sequence models under a unified protocol. Gait data were collected from 60 healthy adults under three metronome-guided cadence conditions. Ten bilateral lower-limb joint angles were used as inputs, and OpenSim-derived hip muscle forces and hip joint moments were used as reference outputs. Three deep learning models of LSTM, Transformer, and Mamba were trained and evaluated using the same subject-level split, preprocessing pipeline, and metrics. The best model was then directly tested on an external cohort of 9 patients with osteonecrosis of the femoral head (ONFH) without retraining. In the healthy-subject benchmark, Transformer achieved the best subject-level mean performance for both hip muscle force prediction (RMSE = 1.33 N/kg, MAE = 0.57 N/kg, R2 = 0.819) and hip joint moment prediction (RMSE = 0.11 Nm/kg, MAE = 0.07 Nm/kg, R2 = 0.862), with similar advantages across walking cadences. In zero-shot external validation, Transformer retained moderate predictive ability in ONFH for hip muscle force prediction (RMSE = 1.51 N/kg, MAE = 0.70 N/kg, R2 = 0.537) and hip joint moment prediction (RMSE = 0.17 Nm/kg, MAE = 0.12 Nm/kg, R2 = 0.569). These findings support the feasibility of estimating hip dynamics from gait kinematics, identify Transformer as a strong baseline, and highlight the need for broader pathological validation and improved generalization before clinical application.

Hao Yu, Zheng Qin, Ji Hou et al.

The intrinsic rotation invariance lies at the core of matching point clouds with handcrafted descriptors. However, it is widely despised by recent deep matchers that obtain the rotation invariance extrinsically via data augmentation. As the finite number of augmented rotations can never span the continuous SO(3) space, these methods usually show instability when facing rotations that are rarely seen. To this end, we introduce RoITr, a Rotation-Invariant Transformer to cope with the pose variations in the point cloud matching task. We contribute both on the local and global levels. Starting from the local level, we introduce an attention mechanism embedded with Point Pair Feature (PPF)-based coordinates to describe the pose-invariant geometry, upon which a novel attention-based encoder-decoder architecture is constructed. We further propose a global transformer with rotation-invariant cross-frame spatial awareness learned by the self-attention mechanism, which significantly improves the feature distinctiveness and makes the model robust with respect to the low overlap. Experiments are conducted on both the rigid and non-rigid public benchmarks, where RoITr outperforms all the state-of-the-art models by a considerable margin in the low-overlapping scenarios. Especially when the rotations are enlarged on the challenging 3DLoMatch benchmark, RoITr surpasses the existing methods by at least 13 and 5 percentage points in terms of Inlier Ratio and Registration Recall, respectively.

Ji Hou, Xiaoliang Dai, Zijian He et al.

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to leverage existing large-scale RGB-D data in a self-supervised pre-training to embed these 3D priors into 2D learned feature representations. In contrast to traditional 3D contrastive learning paradigms requiring 3D reconstructions or multi-view correspondences, our approach is simple: we formulate a pre-text reconstruction task by masking RGB and depth patches in individual RGB-D frames. We demonstrate the Mask3D is particularly effective in embedding 3D priors into the powerful 2D ViT backbone, enabling improved representation learning for various scene understanding tasks, such as semantic segmentation, instance segmentation and object detection. Experiments show that Mask3D notably outperforms existing self-supervised 3D pre-training approaches on ScanNet, NYUv2, and Cityscapes image understanding tasks, with an improvement of +6.5% mIoU against the state-of-the-art Pri3D on ScanNet image semantic segmentation.

Hao Yu, Ji Hou, Zheng Qin et al.

Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8\degree in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch.

Yuanhao Cai, Kunpeng Li, Menglin Jia et al.

Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existing methods mainly based on graphics or prompt extension struggle to generalize beyond simple simulated environments or learn implicit physical reasoning. The scarcity of training data with rich physics interactions and phenomena is also a problem. In this paper, we first introduce a Physics-Augmented video data construction Pipeline, PhyAugPipe, that leverages a vision-language model (VLM) with chain-of-thought reasoning to collect a large-scale training dataset, PhyVidGen-135K. Then we formulate a principled Physics-aware Groupwise Direct Preference Optimization, PhyGDPO, framework that uses real-world video as winning case to guarantee correct physics learning and builds upon the groupwise Plackett-Luce probabilistic model to capture holistic preferences beyond pairwise comparisons. In PhyGDPO, we design a Physics-Guided Rewarding (PGR) scheme that leverages VLM-based physical rewards to direct the optimization to focus on challenging physics cases. In addition, we propose a LoRA-Switch Reference (LoRA-SR) scheme that avoids full-model duplication as reference for efficient DPO training. Experiments show that our method significantly outperforms state-of-the-art open-source methods on PhyGenBench and VideoPhy2. Please check our project page at https://caiyuanhao1998.github.io/project/PhyGDPO for more video results. Our code, models, and data will be released at https://github.com/caiyuanhao1998/Open-PhyGDPO

Yu Zhang, Junle Yu, Xiaolin Huang et al.

In this paper, we introduce PCR-CG: a novel 3D point cloud registration module explicitly embedding the color signals into the geometry representation. Different from previous methods that only use geometry representation, our module is specifically designed to effectively correlate color into geometry for the point cloud registration task. Our key contribution is a 2D-3D cross-modality learning algorithm that embeds the deep features learned from color signals to the geometry representation. With our designed 2D-3D projection module, the pixel features in a square region centered at correspondences perceived from images are effectively correlated with point clouds. In this way, the overlapped regions can be inferred not only from point cloud but also from the texture appearances. Adding color is non-trivial. We compare against a variety of baselines designed for adding color to 3D, such as exhaustively adding per-pixel features or RGB values in an implicit manner. We leverage Predator [25] as the baseline method and incorporate our proposed module onto it. To validate the effectiveness of 2D features, we ablate different 2D pre-trained networks and show a positive correlation between the pre-trained weights and the task performance. Our experimental results indicate a significant improvement of 6.5% registration recall over the baseline method on the 3DLoMatch benchmark. We additionally evaluate our approach on SOTA methods and observe consistent improvements, such as an improvement of 2.4% registration recall over GeoTransformer as well as 3.5% over CoFiNet. Our study reveals a significant advantages of correlating explicit deep color features to the point cloud in the registration task.

Christina Zhang, Simran Motwani, Matthew Yu et al.

Latent diffusion models (LDMs) have made significant advancements in the field of image generation in recent years. One major advantage of LDMs is their ability to operate in a compressed latent space, allowing for more efficient training and deployment. However, despite these advantages, challenges with LDMs still remain. For example, it has been observed that LDMs often generate high-frequency details and complex compositions imperfectly. We hypothesize that one reason for these flaws is due to the fact that all pre- and post-training of LDMs are done in latent space, which is typically $8 \times 8$ lower spatial-resolution than the output images. To address this issue, we propose adding pixel-space supervision in the post-training process to better preserve high-frequency details. Experimentally, we show that adding a pixel-space objective significantly improves both supervised quality fine-tuning and preference-based post-training by a large margin on a state-of-the-art DiT transformer and U-Net diffusion models in both visual quality and visual flaw metrics, while maintaining the same text alignment quality.

Han Lin, Xichen Pan, Ziqi Huang et al.

Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation, however, these powerful core models are typically reduced to global text encoders for diffusion models, leaving most of their reasoning and planning ability unused. This creates a gap: current multimodal LLMs can parse complex layouts, attributes, and knowledge-intensive scenes, yet struggle to generate images or videos with equally precise and structured control. We propose MetaCanvas, a lightweight framework that lets MLLMs reason and plan directly in spatial and spatiotemporal latent spaces and interface tightly with diffusion generators. We empirically implement MetaCanvas on three different diffusion backbones and evaluate it across six tasks, including text-to-image generation, text/image-to-video generation, image/video editing, and in-context video generation, each requiring precise layouts, robust attribute binding, and reasoning-intensive control. MetaCanvas consistently outperforms global-conditioning baselines, suggesting that treating MLLMs as latent-space planners is a promising direction for narrowing the gap between multimodal understanding and generation.

Di Chang, Ji Hou, Aljaz Bozic et al.

We present HairWeaver, a diffusion-based pipeline that animates a single human image with realistic and expressive hair dynamics. While existing methods successfully control body pose, they lack specific control over hair, and as a result, fail to capture the intricate hair motions, resulting in stiff and unrealistic animations. HairWeaver overcomes this limitation using two specialized modules: a Motion-Context-LoRA to integrate motion conditions and a Sim2Real-Domain-LoRA to preserve the subject's photoreal appearance across different data domains. These lightweight components are designed to guide a video diffusion backbone while maintaining its core generative capabilities. By training on a specialized dataset of dynamic human motion generated from a CG simulator, HairWeaver affords fine control over hair motion and ultimately learns to produce highly realistic hair that responds naturally to movement. Comprehensive evaluations demonstrate that our approach sets a new state of the art, producing lifelike human hair animations with dynamic details.

Kaiyu Yue, Menglin Jia, Ji Hou et al.

We introduce the Sphere Encoder, an efficient generative framework capable of producing images in a single forward pass and competing with many-step diffusion models using fewer than five steps. Our approach works by learning an encoder that maps natural images uniformly onto a spherical latent space, and a decoder that maps random latent vectors back to the image space. Trained solely through image reconstruction losses, the model generates an image by simply decoding a random point on the sphere. Our architecture naturally supports conditional generation, and looping the encoder/decoder a few times can further enhance image quality. Across several datasets, the sphere encoder approach yields performance competitive with state of the art diffusions, but with a small fraction of the inference cost. Project page is available at https://sphere-encoder.github.io .

Adam Polyak, Amit Zohar, Andrew Brown et al. · meta-ai

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos.

Philippe Hansen-Estruch, Jiahui Chen, Vivek Ramanujan et al.

Vision Transformer (ViT) autoencoders have emerged as compelling tokenizers for images, offering improved reconstruction over convolutional tokenizers. However, existing ViT tokenizers cannot explore this landscape as performance degrades outside training resolutions, and reliance on adversarial losses prevents stable scaling. ViTok (Hansen-Estruch et al., 2025) found that the compression ratio r mediates a reconstruction-generation trade-off where lower r means better reconstructions but harder generations, so improving tokenizer reconstruction is key to more Pareto-optimal tokenizers. We introduce ViTok-v2, which addresses these limitations with native resolution support via NaFlex for generalization across resolutions and aspect ratios, and a novel DINOv3 perceptual loss that replaces both LPIPS and GAN objectives for stable training at any scale. ViTok-v2 is trained on about 2B images and scaled to 5B parameters, the largest image autoencoder to date. ViTok-v2 matches or exceeds state-of-the-art reconstruction at 256p and outperforms all baselines at 512p and above. In joint scaling experiments with flow matching generators, we show that scaling both the autoencoder and the generator advances the Pareto frontier of this trade-off.

Yuzhong Huang, Chen Liu, Ji Hou et al.

We present UniPlane, a novel method that unifies plane detection and reconstruction from posed monocular videos. Unlike existing methods that detect planes from local observations and associate them across the video for the final reconstruction, UniPlane unifies both the detection and the reconstruction tasks in a single network, which allows us to directly optimize final reconstruction quality and fully leverage temporal information. Specifically, we build a Transformers-based deep neural network that jointly constructs a 3D feature volume for the environment and estimates a set of per-plane embeddings as queries. UniPlane directly reconstructs the 3D planes by taking dot products between voxel embeddings and the plane embeddings followed by binary thresholding. Extensive experiments on real-world datasets demonstrate that UniPlane outperforms state-of-the-art methods in both plane detection and reconstruction tasks, achieving +4.6 in F-score in geometry as well as consistent improvements in other geometry and segmentation metrics.

Felix Wimbauer, Bichen Wu, Edgar Schoenfeld et al.

Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A large image-to-image network has to be applied many times to iteratively refine an image from random noise. While many recent works propose techniques to reduce the number of required steps, they generally treat the underlying denoising network as a black box. In this work, we investigate the behavior of the layers within the network and find that 1) the layers' output changes smoothly over time, 2) the layers show distinct patterns of change, and 3) the change from step to step is often very small. We hypothesize that many layer computations in the denoising network are redundant. Leveraging this, we introduce block caching, in which we reuse outputs from layer blocks of previous steps to speed up inference. Furthermore, we propose a technique to automatically determine caching schedules based on each block's changes over timesteps. In our experiments, we show through FID, human evaluation and qualitative analysis that Block Caching allows to generate images with higher visual quality at the same computational cost. We demonstrate this for different state-of-the-art models (LDM and EMU) and solvers (DDIM and DPM).

Xichen Pan, Satya Narayan Shukla, Aashu Singh et al.

Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often demands complex training recipes and careful data balancing. We introduce MetaQueries, a set of learnable queries that act as an efficient interface between autoregressive multimodal LLMs (MLLMs) and diffusion models. MetaQueries connects the MLLM's latents to the diffusion decoder, enabling knowledge-augmented image generation by leveraging the MLLM's deep understanding and reasoning capabilities. Our method simplifies training, requiring only paired image-caption data and standard diffusion objectives. Notably, this transfer is effective even when the MLLM backbone remains frozen, thereby preserving its state-of-the-art multimodal understanding capabilities while achieving strong generative performance. Additionally, our method is flexible and can be easily instruction-tuned for advanced applications such as image editing and subject-driven generation.

Tao Li, Chunze Zhang, Weiwei Yao et al.

Understanding efficient fish locomotion offers insights for biomechanics, fluid dynamics, and engineering. Traditional studies often miss the link between neuromuscular control and whole-body movement. To explore energy transfer in carangiform swimming, we created a bio-inspired digital trout. This model combined multibody dynamics, Hill-type muscle modeling, and a high-fidelity fluid-structure interaction algorithm, accurately replicating a real trout's form and properties. Using deep reinforcement learning, the trout's neural system achieved hierarchical spatiotemporal control of muscle activation. We systematically examined how activation strategies affect speed and energy use. Results show that axial myomere coupling-with activation spanning over 0.5 body lengths-is crucial for stable body wave propagation. Moderate muscle contraction duration ([0.1,0.3] of a tail-beat cycle) lets the body and fluid act as a passive damping system, cutting energy use. Additionally, the activation phase lag of myomeres shapes the body wave; if too large, it causes antagonistic contractions that hinder thrust. These findings advance bio-inspired locomotion understanding and aid energy-efficient underwater system design.

Jonas Schult, Sam Tsai, Lukas Höllein et al.

Manually creating 3D environments for AR/VR applications is a complex process requiring expert knowledge in 3D modeling software. Pioneering works facilitate this process by generating room meshes conditioned on textual style descriptions. Yet, many of these automatically generated 3D meshes do not adhere to typical room layouts, compromising their plausibility, e.g., by placing several beds in one bedroom. To address these challenges, we present ControlRoom3D, a novel method to generate high-quality room meshes. Central to our approach is a user-defined 3D semantic proxy room that outlines a rough room layout based on semantic bounding boxes and a textual description of the overall room style. Our key insight is that when rendered to 2D, this 3D representation provides valuable geometric and semantic information to control powerful 2D models to generate 3D consistent textures and geometry that aligns well with the proxy room. Backed up by an extensive study including quantitative metrics and qualitative user evaluations, our method generates diverse and globally plausible 3D room meshes, thus empowering users to design 3D rooms effortlessly without specialized knowledge.

Hongjie Wang, Chih-Yao Ma, Yen-Cheng Liu et al.

Text-to-video generation enhances content creation but is highly computationally intensive: The computational cost of Diffusion Transformers (DiTs) scales quadratically in the number of pixels. This makes minute-length video generation extremely expensive, limiting most existing models to generating videos of only 10-20 seconds length. We propose a Linear-complexity text-to-video Generation (LinGen) framework whose cost scales linearly in the number of pixels. For the first time, LinGen enables high-resolution minute-length video generation on a single GPU without compromising quality. It replaces the computationally-dominant and quadratic-complexity block, self-attention, with a linear-complexity block called MATE, which consists of an MA-branch and a TE-branch. The MA-branch targets short-to-long-range correlations, combining a bidirectional Mamba2 block with our token rearrangement method, Rotary Major Scan, and our review tokens developed for long video generation. The TE-branch is a novel TEmporal Swin Attention block that focuses on temporal correlations between adjacent tokens and medium-range tokens. The MATE block addresses the adjacency preservation issue of Mamba and improves the consistency of generated videos significantly. Experimental results show that LinGen outperforms DiT (with a 75.6% win rate) in video quality with up to 15$\times$ (11.5$\times$) FLOPs (latency) reduction. Furthermore, both automatic metrics and human evaluation demonstrate our LinGen-4B yields comparable video quality to state-of-the-art models (with a 50.5%, 52.1%, 49.1% win rate with respect to Gen-3, LumaLabs, and Kling, respectively). This paves the way to hour-length movie generation and real-time interactive video generation. We provide 68s video generation results and more examples in our project website: https://lineargen.github.io/.

Xu Ma, Peize Sun, Haoyu Ma et al.

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image tokens required for AR models, which constrains both training and inference efficiency, as well as image resolution. To address this, we present Token-Shuffle, a novel yet simple method that reduces the number of image tokens in Transformer. Our key insight is the dimensional redundancy of visual vocabularies in Multimodal Large Language Models (MLLMs), where low-dimensional visual codes from visual encoder are directly mapped to high-dimensional language vocabularies. Leveraging this, we consider two key operations: token-shuffle, which merges spatially local tokens along channel dimension to decrease the input token number, and token-unshuffle, which untangles the inferred tokens after Transformer blocks to restore the spatial arrangement for output. Jointly training with textual prompts, our strategy requires no additional pretrained text-encoder and enables MLLMs to support extremely high-resolution image synthesis in a unified next-token prediction way while maintaining efficient training and inference. For the first time, we push the boundary of AR text-to-image generation to a resolution of 2048x2048 with gratifying generation performance. In GenAI-benchmark, our 2.7B model achieves 0.77 overall score on hard prompts, outperforming AR models LlamaGen by 0.18 and diffusion models LDM by 0.15. Exhaustive large-scale human evaluations also demonstrate our prominent image generation ability in terms of text-alignment, visual flaw, and visual appearance. We hope that Token-Shuffle can serve as a foundational design for efficient high-resolution image generation within MLLMs.

Cong Wei, Bo Sun, Haoyu Ma et al.

Recent advancements in video generation have achieved impressive motion realism, yet they often overlook character-driven storytelling, a crucial task for automated film, animation generation. We introduce Talking Characters, a more realistic task to generate talking character animations directly from speech and text. Unlike talking head, Talking Characters aims at generating the full portrait of one or more characters beyond the facial region. In this paper, we propose MoCha, the first of its kind to generate talking characters. To ensure precise synchronization between video and speech, we propose a speech-video window attention mechanism that effectively aligns speech and video tokens. To address the scarcity of large-scale speech-labeled video datasets, we introduce a joint training strategy that leverages both speech-labeled and text-labeled video data, significantly improving generalization across diverse character actions. We also design structured prompt templates with character tags, enabling, for the first time, multi-character conversation with turn-based dialogue-allowing AI-generated characters to engage in context-aware conversations with cinematic coherence. Extensive qualitative and quantitative evaluations, including human preference studies and benchmark comparisons, demonstrate that MoCha sets a new standard for AI-generated cinematic storytelling, achieving superior realism, expressiveness, controllability and generalization.

Akio Kodaira, Tingbo Hou, Ji Hou et al.

Recently, great progress has been achieved in text-to-video (T2V) generation by scaling transformer-based diffusion models to billions of parameters, which can generate high-quality videos. However, existing models typically produce only short clips offline, restricting their use cases in interactive and real-time applications. This paper addresses these challenges by proposing StreamDiT, a streaming video generation model. StreamDiT training is based on flow matching by adding a moving buffer. We design mixed training with different partitioning schemes of buffered frames to boost both content consistency and visual quality. StreamDiT modeling is based on adaLN DiT with varying time embedding and window attention. To practice the proposed method, we train a StreamDiT model with 4B parameters. In addition, we propose a multistep distillation method tailored for StreamDiT. Sampling distillation is performed in each segment of a chosen partitioning scheme. After distillation, the total number of function evaluations (NFEs) is reduced to the number of chunks in a buffer. Finally, our distilled model reaches real-time performance at 16 FPS on one GPU, which can generate video streams at 512p resolution. We evaluate our method through both quantitative metrics and human evaluation. Our model enables real-time applications, e.g. streaming generation, interactive generation, and video-to-video. We provide video results and more examples in our project website: https://cumulo-autumn.github.io/StreamDiT/

Feng Liang, Haoyu Ma, Zecheng He et al.

Video personalization, which generates customized videos using reference images, has gained significant attention. However, prior methods typically focus on single-concept personalization, limiting broader applications that require multi-concept integration. Attempts to extend these models to multiple concepts often lead to identity blending, which results in composite characters with fused attributes from multiple sources. This challenge arises due to the lack of a mechanism to link each concept with its specific reference image. We address this with anchored prompts, which embed image anchors as unique tokens within text prompts, guiding accurate referencing during generation. Additionally, we introduce concept embeddings to encode the order of reference images. Our approach, Movie Weaver, seamlessly weaves multiple concepts-including face, body, and animal images-into one video, allowing flexible combinations in a single model. The evaluation shows that Movie Weaver outperforms existing methods for multi-concept video personalization in identity preservation and overall quality.

Manuel Dahnert, Ji Hou, Matthias Nießner et al.

Understanding 3D scenes from a single image is fundamental to a wide variety of tasks, such as for robotics, motion planning, or augmented reality. Existing works in 3D perception from a single RGB image tend to focus on geometric reconstruction only, or geometric reconstruction with semantic segmentation or instance segmentation. Inspired by 2D panoptic segmentation, we propose to unify the tasks of geometric reconstruction, 3D semantic segmentation, and 3D instance segmentation into the task of panoptic 3D scene reconstruction - from a single RGB image, predicting the complete geometric reconstruction of the scene in the camera frustum of the image, along with semantic and instance segmentations. We thus propose a new approach for holistic 3D scene understanding from a single RGB image which learns to lift and propagate 2D features from an input image to a 3D volumetric scene representation. We demonstrate that this holistic view of joint scene reconstruction, semantic, and instance segmentation is beneficial over treating the tasks independently, thus outperforming alternative approaches.

Ji Hou, Saining Xie, Benjamin Graham et al.

Recent advances in 3D perception have shown impressive progress in understanding geometric structures of 3Dshapes and even scenes. Inspired by these advances in geometric understanding, we aim to imbue image-based perception with representations learned under geometric constraints. We introduce an approach to learn view-invariant,geometry-aware representations for network pre-training, based on multi-view RGB-D data, that can then be effectively transferred to downstream 2D tasks. We propose to employ contrastive learning under both multi-view im-age constraints and image-geometry constraints to encode3D priors into learned 2D representations. This results not only in improvement over 2D-only representation learning on the image-based tasks of semantic segmentation, instance segmentation, and object detection on real-world in-door datasets, but moreover, provides significant improvement in the low data regime. We show a significant improvement of 6.0% on semantic segmentation on full data as well as 11.9% on 20% data against baselines on ScanNet.

Ji Hou, Benjamin Graham, Matthias Nießner et al.

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be accessed and scanned might be limited; even given sufficient data, acquiring 3D labels (e.g. instance masks) requires intensive human labor. In this paper, we explore data-efficient learning for 3D point cloud. As a first step towards this direction, we propose Contrastive Scene Contexts, a 3D pre-training method that makes use of both point-level correspondences and spatial contexts in a scene. Our method achieves state-of-the-art results on a suite of benchmarks where training data or labels are scarce. Our study reveals that exhaustive labelling of 3D point clouds might be unnecessary; and remarkably, on ScanNet, even using 0.1% of point labels, we still achieve 89% (instance segmentation) and 96% (semantic segmentation) of the baseline performance that uses full annotations.

Yinyu Nie, Ji Hou, Xiaoguang Han et al.

Semantic scene understanding from point clouds is particularly challenging as the points reflect only a sparse set of the underlying 3D geometry. Previous works often convert point cloud into regular grids (e.g. voxels or bird-eye view images), and resort to grid-based convolutions for scene understanding. In this work, we introduce RfD-Net that jointly detects and reconstructs dense object surfaces directly from raw point clouds. Instead of representing scenes with regular grids, our method leverages the sparsity of point cloud data and focuses on predicting shapes that are recognized with high objectness. With this design, we decouple the instance reconstruction into global object localization and local shape prediction. It not only eases the difficulty of learning 2-D manifold surfaces from sparse 3D space, the point clouds in each object proposal convey shape details that support implicit function learning to reconstruct any high-resolution surfaces. Our experiments indicate that instance detection and reconstruction present complementary effects, where the shape prediction head shows consistent effects on improving object detection with modern 3D proposal network backbones. The qualitative and quantitative evaluations further demonstrate that our approach consistently outperforms the state-of-the-arts and improves over 11 of mesh IoU in object reconstruction.

Nika Dogonadze, Jana Obernosterer, Ji Hou

Rapid progress in deep learning is continuously making it easier and cheaper to generate video forgeries. Hence, it becomes very important to have a reliable way of detecting these forgeries. This paper describes such an approach for various tampering scenarios. The problem is modelled as a per-frame binary classification task. We propose to use transfer learning from face recognition task to improve tampering detection on many different facial manipulation scenarios. Furthermore, in low resolution settings, where single frame detection performs poorly, we try to make use of neighboring frames for middle frame classification. We evaluate both approaches on the public FaceForensics benchmark, achieving state of the art accuracy.

Ji Hou, Angela Dai, Matthias Nießner

During 3D reconstruction, it is often the case that people cannot scan each individual object from all views, resulting in missing geometry in the captured scan. This missing geometry can be fundamentally limiting for many applications, e.g., a robot needs to know the unseen geometry to perform a precise grasp on an object. Thus, we introduce the task of semantic instance completion: from an incomplete RGB-D scan of a scene, we aim to detect the individual object instances and infer their complete object geometry. This will open up new possibilities for interactions with objects in a scene, for instance for virtual or robotic agents. We tackle this problem by introducing RevealNet, a new data-driven approach that jointly detects object instances and predicts their complete geometry. This enables a semantically meaningful decomposition of a scanned scene into individual, complete 3D objects, including hidden and unobserved object parts. RevealNet is an end-to-end 3D neural network architecture that leverages joint color and geometry feature learning. The fully-convolutional nature of our 3D network enables efficient inference of semantic instance completion for 3D scans at scale of large indoor environments in a single forward pass. We show that predicting complete object geometry improves both 3D detection and instance segmentation performance. We evaluate on both real and synthetic scan benchmark data for the new task, where we outperform state-of-the-art approaches by over 15 in mAP@0.5 on ScanNet, and over 18 in mAP@0.5 on SUNCG.

Ji Hou, Angela Dai, Matthias Nießner

We introduce 3D-SIS, a novel neural network architecture for 3D semantic instance segmentation in commodity RGB-D scans. The core idea of our method is to jointly learn from both geometric and color signal, thus enabling accurate instance predictions. Rather than operate solely on 2D frames, we observe that most computer vision applications have multi-view RGB-D input available, which we leverage to construct an approach for 3D instance segmentation that effectively fuses together these multi-modal inputs. Our network leverages high-resolution RGB input by associating 2D images with the volumetric grid based on the pose alignment of the 3D reconstruction. For each image, we first extract 2D features for each pixel with a series of 2D convolutions; we then backproject the resulting feature vector to the associated voxel in the 3D grid. This combination of 2D and 3D feature learning allows significantly higher accuracy object detection and instance segmentation than state-of-the-art alternatives. We show results on both synthetic and real-world public benchmarks, achieving an improvement in mAP of over 13 on real-world data.