Ji Hou

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.

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.

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.

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.

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.