P. Vajda

Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo et al.

Real-time multi-task multi-model (MTMM) workloads, a new form of deep learning inference workloads, are emerging for applications areas like extended reality (XR) to support metaverse use cases. These workloads combine user interactivity with computationally complex machine learning (ML) activities. Compared to standard ML applications, these ML workloads present unique difficulties and constraints. Real-time MTMM workloads impose heterogeneity and concurrency requirements on future ML systems and devices, necessitating the development of new capabilities. This paper begins with a discussion of the various characteristics of these real-time MTMM ML workloads and presents an ontology for evaluating the performance of future ML hardware for XR systems. Next, we present XRBENCH, a collection of MTMM ML tasks, models, and usage scenarios that execute these models in three representative ways: cascaded, concurrent, and cascaded-concurrent for XR use cases. Finally, we emphasize the need for new metrics that capture the requirements properly. We hope that our work will stimulate research and lead to the development of a new generation of ML systems for XR use cases. XRBench is available as an open-source project: https://github.com/XRBench

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.

Zecheng He, Bo Sun, Felix Juefei-Xu et al. · meta-ai

Diffusion models have demonstrated remarkable efficacy across various image-to-image tasks. In this research, we introduce Imagine yourself, a state-of-the-art model designed for personalized image generation. Unlike conventional tuning-based personalization techniques, Imagine yourself operates as a tuning-free model, enabling all users to leverage a shared framework without individualized adjustments. Moreover, previous work met challenges balancing identity preservation, following complex prompts and preserving good visual quality, resulting in models having strong copy-paste effect of the reference images. Thus, they can hardly generate images following prompts that require significant changes to the reference image, \eg, changing facial expression, head and body poses, and the diversity of the generated images is low. To address these limitations, our proposed method introduces 1) a new synthetic paired data generation mechanism to encourage image diversity, 2) a fully parallel attention architecture with three text encoders and a fully trainable vision encoder to improve the text faithfulness, and 3) a novel coarse-to-fine multi-stage finetuning methodology that gradually pushes the boundary of visual quality. Our study demonstrates that Imagine yourself surpasses the state-of-the-art personalization model, exhibiting superior capabilities in identity preservation, visual quality, and text alignment. This model establishes a robust foundation for various personalization applications. Human evaluation results validate the model's SOTA superiority across all aspects (identity preservation, text faithfulness, and visual appeal) compared to the previous personalization models.

Yu-Jhe Li, Tao Xu, Bichen Wu et al. · cmu

We tackle the task of NeRF inversion for style-based neural radiance fields, (e.g., StyleNeRF). In the task, we aim to learn an inversion function to project an input image to the latent space of a NeRF generator and then synthesize novel views of the original image based on the latent code. Compared with GAN inversion for 2D generative models, NeRF inversion not only needs to 1) preserve the identity of the input image, but also 2) ensure 3D consistency in generated novel views. This requires the latent code obtained from the single-view image to be invariant across multiple views. To address this new challenge, we propose a two-stage encoder for style-based NeRF inversion. In the first stage, we introduce a base encoder that converts the input image to a latent code. To ensure the latent code is view-invariant and is able to synthesize 3D consistent novel view images, we utilize identity contrastive learning to train the base encoder. Second, to better preserve the identity of the input image, we introduce a refining encoder to refine the latent code and add finer details to the output image. Importantly note that the novelty of this model lies in the design of its first-stage encoder which produces the closest latent code lying on the latent manifold and thus the refinement in the second stage would be close to the NeRF manifold. Through extensive experiments, we demonstrate that our proposed two-stage encoder qualitatively and quantitatively exhibits superiority over the existing encoders for inversion in both image reconstruction and novel-view rendering.

Feng Liang, Bichen Wu, Xiaoliang Dai et al.

Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and then leverage pre-trained vision-language models, e.g., CLIP, to classify masked regions. We identify the performance bottleneck of this paradigm to be the pre-trained CLIP model, since it does not perform well on masked images. To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions. We collect training data by mining an existing image-caption dataset (e.g., COCO Captions), using CLIP to match masked image regions to nouns in the image captions. Compared with the more precise and manually annotated segmentation labels with fixed classes (e.g., COCO-Stuff), we find our noisy but diverse dataset can better retain CLIP's generalization ability. Along with finetuning the entire model, we utilize the "blank" areas in masked images using a method we dub mask prompt tuning. Experiments demonstrate mask prompt tuning brings significant improvement without modifying any weights of CLIP, and it can further improve a fully finetuned model. In particular, when trained on COCO and evaluated on ADE20K-150, our best model achieves 29.6% mIoU, which is +8.5% higher than the previous state-of-the-art. For the first time, open-vocabulary generalist models match the performance of supervised specialist models in 2017 without dataset-specific adaptations.

Sayan Ghosh, Karthik Prasad, Xiaoliang Dai et al. · oxford

Neural network pruning is frequently used to compress over-parameterized networks by large amounts, while incurring only marginal drops in generalization performance. However, the impact of pruning on networks that have been highly optimized for efficient inference has not received the same level of attention. In this paper, we analyze the effect of pruning for computer vision, and study state-of-the-art ConvNets, such as the FBNetV3 family of models. We show that model pruning approaches can be used to further optimize networks trained through NAS (Neural Architecture Search). The resulting family of pruned models can consistently obtain better performance than existing FBNetV3 models at the same level of computation, and thus provide state-of-the-art results when trading off between computational complexity and generalization performance on the ImageNet benchmark. In addition to better generalization performance, we also demonstrate that when limited computation resources are available, pruning FBNetV3 models incur only a fraction of GPU-hours involved in running a full-scale NAS.

Jialiang Wang, Daniel Scharstein, Akash Bapat et al.

We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with a fallback to monocular depth estimation when rectification is unreliable. The output of our depth sensing system is then used in a novel view generation pipeline to create 3D computational photography effects using point-of-view images captured by smart glasses. All these steps are executed on-device on the stringent compute budget of a mobile phone, and because we expect the users can use a wide range of smartphones, our design needs to be general and cannot be dependent on a particular hardware or ML accelerator such as a smartphone GPU. Although each of these steps is well studied, a description of a practical system is still lacking. For such a system, all these steps need to work in tandem with one another and fallback gracefully on failures within the system or less than ideal input data. We show how we handle unforeseen changes to calibration, e.g., due to heat, robustly support depth estimation in the wild, and still abide by the memory and latency constraints required for a smooth user experience. We show that our trained models are fast, and run in less than 1s on a six-year-old Samsung Galaxy S8 phone's CPU. Our models generalize well to unseen data and achieve good results on Middlebury and in-the-wild images captured from the smart glasses.

Yen-Cheng Liu, Chih-Yao Ma, Xiaoliang Dai et al.

Recent developments for Semi-Supervised Object Detection (SSOD) have shown the promise of leveraging unlabeled data to improve an object detector. However, thus far these methods have assumed that the unlabeled data does not contain out-of-distribution (OOD) classes, which is unrealistic with larger-scale unlabeled datasets. In this paper, we consider a more practical yet challenging problem, Open-Set Semi-Supervised Object Detection (OSSOD). We first find the existing SSOD method obtains a lower performance gain in open-set conditions, and this is caused by the semantic expansion, where the distracting OOD objects are mispredicted as in-distribution pseudo-labels for the semi-supervised training. To address this problem, we consider online and offline OOD detection modules, which are integrated with SSOD methods. With the extensive studies, we found that leveraging an offline OOD detector based on a self-supervised vision transformer performs favorably against online OOD detectors due to its robustness to the interference of pseudo-labeling. In the experiment, our proposed framework effectively addresses the semantic expansion issue and shows consistent improvements on many OSSOD benchmarks, including large-scale COCO-OpenImages. We also verify the effectiveness of our framework under different OSSOD conditions, including varying numbers of in-distribution classes, different degrees of supervision, and different combinations of unlabeled sets.

Haoran You, Yunyang Xiong, Xiaoliang Dai et al.

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a quadratic complexity with the number of input tokens. Existing efficient ViTs adopt local attention (e.g., Swin) or linear attention (e.g., Performer), which sacrifice ViTs' capabilities of capturing either global or local context. In this work, we ask an important research question: Can ViTs learn both global and local context while being more efficient during inference? To this end, we propose a framework called Castling-ViT, which trains ViTs using both linear-angular attention and masked softmax-based quadratic attention, but then switches to having only linear angular attention during ViT inference. Our Castling-ViT leverages angular kernels to measure the similarities between queries and keys via spectral angles. And we further simplify it with two techniques: (1) a novel linear-angular attention mechanism: we decompose the angular kernels into linear terms and high-order residuals, and only keep the linear terms; and (2) we adopt two parameterized modules to approximate high-order residuals: a depthwise convolution and an auxiliary masked softmax attention to help learn both global and local information, where the masks for softmax attention are regularized to gradually become zeros and thus incur no overhead during ViT inference. Extensive experiments and ablation studies on three tasks consistently validate the effectiveness of the proposed Castling-ViT, e.g., achieving up to a 1.8% higher accuracy or 40% MACs reduction on ImageNet classification and 1.2 higher mAP on COCO detection under comparable FLOPs, as compared to ViTs with vanilla softmax-based attentions.

Chaojian Li, Bichen Wu, Albert Pumarola et al.

We present a method that accelerates reconstruction of 3D scenes and objects, aiming to enable instant reconstruction on edge devices such as mobile phones and AR/VR headsets. While recent works have accelerated scene reconstruction training to minute/second-level on high-end GPUs, there is still a large gap to the goal of instant training on edge devices which is yet highly desired in many emerging applications such as immersive AR/VR. To this end, this work aims to further accelerate training by leveraging geometry priors of the target scene. Our method proposes strategies to alleviate the noise of the imperfect geometry priors to accelerate the training speed on top of the highly optimized Instant-NGP. On the NeRF Synthetic dataset, our work uses half of the training iterations to reach an average test PSNR of >30.

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.

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.

Chenfeng Xu, Shijia Yang, Tomer Galanti et al.

3D point-clouds and 2D images are different visual representations of the physical world. While human vision can understand both representations, computer vision models designed for 2D image and 3D point-cloud understanding are quite different. Our paper explores the potential of transferring 2D model architectures and weights to understand 3D point-clouds, by empirically investigating the feasibility of the transfer, the benefits of the transfer, and shedding light on why the transfer works. We discover that we can indeed use the same architecture and pretrained weights of a neural net model to understand both images and point-clouds. Specifically, we transfer the image-pretrained model to a point-cloud model by copying or inflating the weights. We find that finetuning the transformed image-pretrained models (FIP) with minimal efforts -- only on input, output, and normalization layers -- can achieve competitive performance on 3D point-cloud classification, beating a wide range of point-cloud models that adopt task-specific architectures and use a variety of tricks. When finetuning the whole model, the performance improves even further. Meanwhile, FIP improves data efficiency, reaching up to 10.0 top-1 accuracy percent on few-shot classification. It also speeds up the training of point-cloud models by up to 11.1x for a target accuracy (e.g., 90 % accuracy). Lastly, we provide an explanation of the image to point-cloud transfer from the aspect of neural collapse. The code is available at: \url{https://github.com/chenfengxu714/image2point}.

Feng Liang, Bichen Wu, Jialiang Wang et al.

Diffusion models have transformed the image-to-image (I2I) synthesis and are now permeating into videos. However, the advancement of video-to-video (V2V) synthesis has been hampered by the challenge of maintaining temporal consistency across video frames. This paper proposes a consistent V2V synthesis framework by jointly leveraging spatial conditions and temporal optical flow clues within the source video. Contrary to prior methods that strictly adhere to optical flow, our approach harnesses its benefits while handling the imperfection in flow estimation. We encode the optical flow via warping from the first frame and serve it as a supplementary reference in the diffusion model. This enables our model for video synthesis by editing the first frame with any prevalent I2I models and then propagating edits to successive frames. Our V2V model, FlowVid, demonstrates remarkable properties: (1) Flexibility: FlowVid works seamlessly with existing I2I models, facilitating various modifications, including stylization, object swaps, and local edits. (2) Efficiency: Generation of a 4-second video with 30 FPS and 512x512 resolution takes only 1.5 minutes, which is 3.1x, 7.2x, and 10.5x faster than CoDeF, Rerender, and TokenFlow, respectively. (3) High-quality: In user studies, our FlowVid is preferred 45.7% of the time, outperforming CoDeF (3.5%), Rerender (10.2%), and TokenFlow (40.4%).

Bichen Wu, Ching-Yao Chuang, Xiaoyan Wang et al.

In this paper, we introduce Fairy, a minimalist yet robust adaptation of image-editing diffusion models, enhancing them for video editing applications. Our approach centers on the concept of anchor-based cross-frame attention, a mechanism that implicitly propagates diffusion features across frames, ensuring superior temporal coherence and high-fidelity synthesis. Fairy not only addresses limitations of previous models, including memory and processing speed. It also improves temporal consistency through a unique data augmentation strategy. This strategy renders the model equivariant to affine transformations in both source and target images. Remarkably efficient, Fairy generates 120-frame 512x384 videos (4-second duration at 30 FPS) in just 14 seconds, outpacing prior works by at least 44x. A comprehensive user study, involving 1000 generated samples, confirms that our approach delivers superior quality, decisively outperforming established methods.

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/.

Philippe Hansen-Estruch, David Yan, Ching-Yao Chung et al.

Visual tokenization via auto-encoding empowers state-of-the-art image and video generative models by compressing pixels into a latent space. Although scaling Transformer-based generators has been central to recent advances, the tokenizer component itself is rarely scaled, leaving open questions about how auto-encoder design choices influence both its objective of reconstruction and downstream generative performance. Our work aims to conduct an exploration of scaling in auto-encoders to fill in this blank. To facilitate this exploration, we replace the typical convolutional backbone with an enhanced Vision Transformer architecture for Tokenization (ViTok). We train ViTok on large-scale image and video datasets far exceeding ImageNet-1K, removing data constraints on tokenizer scaling. We first study how scaling the auto-encoder bottleneck affects both reconstruction and generation -- and find that while it is highly correlated with reconstruction, its relationship with generation is more complex. We next explored the effect of separately scaling the auto-encoders' encoder and decoder on reconstruction and generation performance. Crucially, we find that scaling the encoder yields minimal gains for either reconstruction or generation, while scaling the decoder boosts reconstruction but the benefits for generation are mixed. Building on our exploration, we design ViTok as a lightweight auto-encoder that achieves competitive performance with state-of-the-art auto-encoders on ImageNet-1K and COCO reconstruction tasks (256p and 512p) while outperforming existing auto-encoders on 16-frame 128p video reconstruction for UCF-101, all with 2-5x fewer FLOPs. When integrated with Diffusion Transformers, ViTok demonstrates competitive performance on image generation for ImageNet-1K and sets new state-of-the-art benchmarks for class-conditional video generation on UCF-101.

Bichen Wu, Ruizhe Cheng, Peizhao Zhang et al.

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts than supervised "gold" labels. Previous works, such as CLIP, use InfoNCE loss to train a model to predict the pairing between images and text captions. CLIP, however, is data hungry and requires more than 400M image-text pairs for training. The inefficiency can be partially attributed to the fact that the image-text pairs are noisy. To address this, we propose OTTER (Optimal TransporT distillation for Efficient zero-shot Recognition), which uses online entropic optimal transport to find a soft image-text match as labels for contrastive learning. Based on pretrained image and text encoders, models trained with OTTER achieve strong performance with only 3M image text pairs. Compared with InfoNCE loss, label smoothing, and knowledge distillation, OTTER consistently outperforms these baselines in zero shot evaluation on Google Open Images (19,958 classes) and multi-labeled ImageNet 10K (10032 classes) from Tencent ML-Images. Over 42 evaluations on 7 different dataset/architecture settings x 6 metrics, OTTER outperforms (32) or ties (2) all baselines in 34 of them.

Yu-Jhe Li, Xiaoliang Dai, Chih-Yao Ma et al.

We address the task of domain adaptation in object detection, where there is a domain gap between a domain with annotations (source) and a domain of interest without annotations (target). As an effective semi-supervised learning method, the teacher-student framework (a student model is supervised by the pseudo labels from a teacher model) has also yielded a large accuracy gain in cross-domain object detection. However, it suffers from the domain shift and generates many low-quality pseudo labels (\textit{e.g.,} false positives), which leads to sub-optimal performance. To mitigate this problem, we propose a teacher-student framework named Adaptive Teacher (AT) which leverages domain adversarial learning and weak-strong data augmentation to address the domain gap. Specifically, we employ feature-level adversarial training in the student model, allowing features derived from the source and target domains to share similar distributions. This process ensures the student model produces domain-invariant features. Furthermore, we apply weak-strong augmentation and mutual learning between the teacher model (taking data from the target domain) and the student model (taking data from both domains). This enables the teacher model to learn the knowledge from the student model without being biased to the source domain. We show that AT demonstrates superiority over existing approaches and even Oracle (fully-supervised) models by a large margin. For example, we achieve 50.9% (49.3%) mAP on Foggy Cityscape (Clipart1K), which is 9.2% (5.2%) and 8.2% (11.0%) higher than previous state-of-the-art and Oracle, respectively.

Chenfeng Xu, Bohan Zhai, Bichen Wu et al.

3D point-cloud-based perception is a challenging but crucial computer vision task. A point-cloud consists of a sparse, unstructured, and unordered set of points. To understand a point-cloud, previous point-based methods, such as PointNet++, extract visual features through hierarchically aggregation of local features. However, such methods have several critical limitations: 1) Such methods require several sampling and grouping operations, which slow down the inference speed. 2) Such methods spend an equal amount of computation on each points in a point-cloud, though many of points are redundant. 3) Such methods aggregate local features together through downsampling, which leads to information loss and hurts the perception performance. To overcome these challenges, we propose a novel, simple, and elegant deep learning model called YOGO (You Only Group Once). Compared with previous methods, YOGO only needs to sample and group a point-cloud once, so it is very efficient. Instead of operating on points, YOGO operates on a small number of tokens, each of which summarizes the point features in a sub-region. This allows us to avoid computing on the redundant points and thus boosts efficiency.Moreover, YOGO preserves point-wise features by projecting token features to point features although the computation is performed on tokens. This avoids information loss and can improve point-wise perception performance. We conduct thorough experiments to demonstrate that YOGO achieves at least 3.0x speedup over point-based baselines while delivering competitive classification and segmentation performance on the ModelNet, ShapeNetParts and S3DIS datasets.

Alexander Grabner, Yaming Wang, Peizhao Zhang et al.

We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In contrast to previous methods, we make two main contributions: First, instead of comparing real-world images and synthetic renderings in the RGB or mask space, we compare them in a feature space optimized for 3D pose refinement. Second, we introduce a novel differentiable renderer that learns to approximate the rasterization backward pass from data instead of relying on a hand-crafted algorithm. For this purpose, we predict deep cross-domain correspondences between RGB images and 3D model renderings in the form of what we call geometric correspondence fields. These correspondence fields serve as pixel-level gradients which are analytically propagated backward through the rendering pipeline to perform a gradient-based optimization directly on the 3D pose. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.