Deqing Sun

Kyle Sargent, Zizhang Li, Tanmay Shah et al. · stanford

We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced by in-the-wild multi-object scenes with complex backgrounds. Specifically, we train a generative prior on a mixture of data sources that capture object-centric, indoor, and outdoor scenes. To address issues from data mixture such as depth-scale ambiguity, we propose a novel camera conditioning parameterization and normalization scheme. Further, we observe that Score Distillation Sampling (SDS) tends to truncate the distribution of complex backgrounds during distillation of 360-degree scenes, and propose "SDS anchoring" to improve the diversity of synthesized novel views. Our model sets a new state-of-the-art result in LPIPS on the DTU dataset in the zero-shot setting, even outperforming methods specifically trained on DTU. We further adapt the challenging Mip-NeRF 360 dataset as a new benchmark for single-image novel view synthesis, and demonstrate strong performance in this setting. Our code and data are at http://kylesargent.github.io/zeronvs/

Saurabh Saxena, Charles Herrmann, Junhwa Hur et al.

Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly, without task-specific architectures and loss functions that are predominant for these tasks. Compared to the point estimates of conventional regression-based methods, diffusion models also enable Monte Carlo inference, e.g., capturing uncertainty and ambiguity in flow and depth. With self-supervised pre-training, the combined use of synthetic and real data for supervised training, and technical innovations (infilling and step-unrolled denoising diffusion training) to handle noisy-incomplete training data, and a simple form of coarse-to-fine refinement, one can train state-of-the-art diffusion models for depth and optical flow estimation. Extensive experiments focus on quantitative performance against benchmarks, ablations, and the model's ability to capture uncertainty and multimodality, and impute missing values. Our model, DDVM (Denoising Diffusion Vision Model), obtains a state-of-the-art relative depth error of 0.074 on the indoor NYU benchmark and an Fl-all outlier rate of 3.26\% on the KITTI optical flow benchmark, about 25\% better than the best published method. For an overview see https://diffusion-vision.github.io.

Yiming Xie, Varun Jampani, Lei Zhong et al.

We present a novel approach named OmniControl for incorporating flexible spatial control signals into a text-conditioned human motion generation model based on the diffusion process. Unlike previous methods that can only control the pelvis trajectory, OmniControl can incorporate flexible spatial control signals over different joints at different times with only one model. Specifically, we propose analytic spatial guidance that ensures the generated motion can tightly conform to the input control signals. At the same time, realism guidance is introduced to refine all the joints to generate more coherent motion. Both the spatial and realism guidance are essential and they are highly complementary for balancing control accuracy and motion realism. By combining them, OmniControl generates motions that are realistic, coherent, and consistent with the spatial constraints. Experiments on HumanML3D and KIT-ML datasets show that OmniControl not only achieves significant improvement over state-of-the-art methods on pelvis control but also shows promising results when incorporating the constraints over other joints.

Junyi Zhang, Charles Herrmann, Junhwa Hur et al.

While pre-trained large-scale vision models have shown significant promise for semantic correspondence, their features often struggle to grasp the geometry and orientation of instances. This paper identifies the importance of being geometry-aware for semantic correspondence and reveals a limitation of the features of current foundation models under simple post-processing. We show that incorporating this information can markedly enhance semantic correspondence performance with simple but effective solutions in both zero-shot and supervised settings. We also construct a new challenging benchmark for semantic correspondence built from an existing animal pose estimation dataset, for both pre-training validating models. Our method achieves a PCK@0.10 score of 65.4 (zero-shot) and 85.6 (supervised) on the challenging SPair-71k dataset, outperforming the state of the art by 5.5p and 11.0p absolute gains, respectively. Our code and datasets are publicly available at: https://telling-left-from-right.github.io/.

Gen Li, Deqing Sun, Laura Sevilla-Lara et al.

We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel objects and affordances. While vision-language models excel at recognizing novel objects and scenes, they often struggle to understand finer levels of granularity such as affordances. To handle this issue, we conduct a comprehensive analysis of existing foundation models, to explore their inherent understanding of affordances and assess the potential for data-limited affordance learning. We then propose a vision-language framework with simple and effective designs that boost the alignment between visual features and affordance text embeddings. Experiments on two affordance segmentation benchmarks show that the proposed method outperforms state-of-the-art models with less than 1% of the full training data, and exhibits reasonable generalization capability on unseen objects and affordances.

Lei Zhong, Yiming Xie, Varun Jampani et al.

We introduce a novel Stylized Motion Diffusion model, dubbed SMooDi, to generate stylized motion driven by content texts and style motion sequences. Unlike existing methods that either generate motion of various content or transfer style from one sequence to another, SMooDi can rapidly generate motion across a broad range of content and diverse styles. To this end, we tailor a pre-trained text-to-motion model for stylization. Specifically, we propose style guidance to ensure that the generated motion closely matches the reference style, alongside a lightweight style adaptor that directs the motion towards the desired style while ensuring realism. Experiments across various applications demonstrate that our proposed framework outperforms existing methods in stylized motion generation.

Cyrus Rashtchian, Charles Herrmann, Chun-Sung Ferng et al.

Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddings. While analysis through the use of probes has become standard in NLP, there has been much less exploration in vision. Image foundation models have primarily been evaluated for semantic content. Better understanding the non-semantic information in popular embeddings (e.g., MAE, SimCLR, or CLIP) will shed new light both on the training algorithms and on the uses for these foundation models. We design a systematic transformation prediction task and measure the visual content of embeddings along many axes, including image style, quality, and a range of natural and artificial transformations. Surprisingly, six embeddings (including SimCLR) encode enough non-semantic information to identify dozens of transformations. We also consider a generalization task, where we group similar transformations and hold out several for testing. We find that image-text models (CLIP and ALIGN) are better at recognizing new examples of style transfer than masking-based models (CAN and MAE). Overall, our results suggest that the choice of pre-training algorithm impacts the types of information in the embedding, and certain models are better than others for non-semantic downstream tasks.

Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan et al.

Recent novel view synthesis methods obtain promising results for relatively small scenes, e.g., indoor environments and scenes with a few objects, but tend to fail for unbounded outdoor scenes with a single image as input. In this paper, we introduce SAMPLING, a Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image based on improved multiplane images (MPI). Observing that depth distribution varies significantly for unbounded outdoor scenes, we employ an adaptive-bins strategy for MPI to arrange planes in accordance with each scene image. To represent intricate geometry and multi-scale details, we further introduce a hierarchical refinement branch, which results in high-quality synthesized novel views. Our method demonstrates considerable performance gains in synthesizing large-scale unbounded outdoor scenes using a single image on the KITTI dataset and generalizes well to the unseen Tanks and Temples dataset.The code and models will soon be made available.

Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan et al.

We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in dynamic driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency. Our project page is at: https://github.com/VDIGPKU/DrivingGaussian.

Zudi Lin, Donglai Wei, Aarush Gupta et al.

Objects with complex structures pose significant challenges to existing instance segmentation methods that rely on boundary or affinity maps, which are vulnerable to small errors around contacting pixels that cause noticeable connectivity change. While the distance transform (DT) makes instance interiors and boundaries more distinguishable, it tends to overlook the intra-object connectivity for instances with varying width and result in over-segmentation. To address these challenges, we propose a skeleton-aware distance transform (SDT) that combines the merits of object skeleton in preserving connectivity and DT in modeling geometric arrangement to represent instances with arbitrary structures. Comprehensive experiments on histopathology image segmentation demonstrate that SDT achieves state-of-the-art performance.

Mohamed El Banani, Amit Raj, Kevis-Kokitsi Maninis et al.

Recent advances in large-scale pretraining have yielded visual foundation models with strong capabilities. Not only can recent models generalize to arbitrary images for their training task, their intermediate representations are useful for other visual tasks such as detection and segmentation. Given that such models can classify, delineate, and localize objects in 2D, we ask whether they also represent their 3D structure? In this work, we analyze the 3D awareness of visual foundation models. We posit that 3D awareness implies that representations (1) encode the 3D structure of the scene and (2) consistently represent the surface across views. We conduct a series of experiments using task-specific probes and zero-shot inference procedures on frozen features. Our experiments reveal several limitations of the current models. Our code and analysis can be found at https://github.com/mbanani/probe3d.

Zhile Ren, Orazio Gallo, Deqing Sun et al.

To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has not yet produced state-of-the-art results. We present a simple, yet effective fusion approach for multi-frame optical flow that benefits from longer-term temporal cues. Our method first warps the optical flow from previous frames to the current, thereby yielding multiple plausible estimates. It then fuses the complementary information carried by these estimates into a new optical flow field. At the time of writing, our method ranks first among published results in the MPI Sintel and KITTI 2015 benchmarks. Our models will be available on https://github.com/NVlabs/PWC-Net.

Deqing Sun, Xiaodong Yang, Ming-Yu Liu et al.

We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training. First, we design a compact but effective CNN model, called PWC-Net, according to simple and well-established principles: pyramidal processing, warping, and cost volume processing. PWC-Net is 17 times smaller in size, 2 times faster in inference, and 11\% more accurate on Sintel final than the recent FlowNet2 model. It is the winning entry in the optical flow competition of the robust vision challenge. Next, we experimentally analyze the sources of our performance gains. In particular, we use the same training procedure of PWC-Net to retrain FlowNetC, a sub-network of FlowNet2. The retrained FlowNetC is 56\% more accurate on Sintel final than the previously trained one and even 5\% more accurate than the FlowNet2 model. We further improve the training procedure and increase the accuracy of PWC-Net on Sintel by 10\% and on KITTI 2012 and 2015 by 20\%. Our newly trained model parameters and training protocols will be available on https://github.com/NVlabs/PWC-Net

Deqing Sun, Xiaodong Yang, Ming-Yu Liu et al.

We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the cur- rent optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow. PWC-Net is 17 times smaller in size and easier to train than the recent FlowNet2 model. Moreover, it outperforms all published optical flow methods on the MPI Sintel final pass and KITTI 2015 benchmarks, running at about 35 fps on Sintel resolution (1024x436) images. Our models are available on https://github.com/NVlabs/PWC-Net.

Xiaoyu Zhou, Xingjian Ran, Yajiao Xiong et al.

We present GALA3D, generative 3D GAussians with LAyout-guided control, for effective compositional text-to-3D generation. We first utilize large language models (LLMs) to generate the initial layout and introduce a layout-guided 3D Gaussian representation for 3D content generation with adaptive geometric constraints. We then propose an instance-scene compositional optimization mechanism with conditioned diffusion to collaboratively generate realistic 3D scenes with consistent geometry, texture, scale, and accurate interactions among multiple objects while simultaneously adjusting the coarse layout priors extracted from the LLMs to align with the generated scene. Experiments show that GALA3D is a user-friendly, end-to-end framework for state-of-the-art scene-level 3D content generation and controllable editing while ensuring the high fidelity of object-level entities within the scene. The source codes and models will be available at gala3d.github.io.

Xiaogang Peng, Yiming Xie, Zizhao Wu et al.

We address the problem of generating realistic 3D human-object interactions (HOIs) driven by textual prompts. To this end, we take a modular design and decompose the complex task into simpler sub-tasks. We first develop a dual-branch diffusion model (HOI-DM) to generate both human and object motions conditioned on the input text, and encourage coherent motions by a cross-attention communication module between the human and object motion generation branches. We also develop an affordance prediction diffusion model (APDM) to predict the contacting area between the human and object during the interactions driven by the textual prompt. The APDM is independent of the results by the HOI-DM and thus can correct potential errors by the latter. Moreover, it stochastically generates the contacting points to diversify the generated motions. Finally, we incorporate the estimated contacting points into the classifier-guidance to achieve accurate and close contact between humans and objects. To train and evaluate our approach, we annotate BEHAVE dataset with text descriptions. Experimental results on BEHAVE and OMOMO demonstrate that our approach produces realistic HOIs with various interactions and different types of objects.

Saurabh Saxena, Junhwa Hur, Charles Herrmann et al.

While methods for monocular depth estimation have made significant strides on standard benchmarks, zero-shot metric depth estimation remains unsolved. Challenges include the joint modeling of indoor and outdoor scenes, which often exhibit significantly different distributions of RGB and depth, and the depth-scale ambiguity due to unknown camera intrinsics. Recent work has proposed specialized multi-head architectures for jointly modeling indoor and outdoor scenes. In contrast, we advocate a generic, task-agnostic diffusion model, with several advancements such as log-scale depth parameterization to enable joint modeling of indoor and outdoor scenes, conditioning on the field-of-view (FOV) to handle scale ambiguity and synthetically augmenting FOV during training to generalize beyond the limited camera intrinsics in training datasets. Furthermore, by employing a more diverse training mixture than is common, and an efficient diffusion parameterization, our method, DMD (Diffusion for Metric Depth) achieves a 25\% reduction in relative error (REL) on zero-shot indoor and 33\% reduction on zero-shot outdoor datasets over the current SOTA using only a small number of denoising steps. For an overview see https://diffusion-vision.github.io/dmd

Xirui Li, Charles Herrmann, Kelvin C. K. Chan et al.

Recent progress in image generation has sparked research into controlling these models through condition signals, with various methods addressing specific challenges in conditional generation. Instead of proposing another specialized technique, we introduce a simple, unified framework to handle diverse conditional generation tasks involving a specific image-condition correlation. By learning a joint distribution over a correlated image pair (e.g. image and depth) with a diffusion model, our approach enables versatile capabilities via different inference-time sampling schemes, including controllable image generation (e.g. depth to image), estimation (e.g. image to depth), signal guidance, joint generation (image & depth), and coarse control. Previous attempts at unification often introduce significant complexity through multi-stage training, architectural modification, or increased parameter counts. In contrast, our simple formulation requires a single, computationally efficient training stage, maintains the standard model input, and adds minimal learned parameters (15% of the base model). Moreover, our model supports additional capabilities like non-spatially aligned and coarse conditioning. Extensive results show that our single model can produce comparable results with specialized methods and better results than prior unified methods. We also demonstrate that multiple models can be effectively combined for multi-signal conditional generation.

Andreas Engelhardt, Amit Raj, Mark Boss et al.

We present SHINOBI, an end-to-end framework for the reconstruction of shape, material, and illumination from object images captured with varying lighting, pose, and background. Inverse rendering of an object based on unconstrained image collections is a long-standing challenge in computer vision and graphics and requires a joint optimization over shape, radiance, and pose. We show that an implicit shape representation based on a multi-resolution hash encoding enables faster and robust shape reconstruction with joint camera alignment optimization that outperforms prior work. Further, to enable the editing of illumination and object reflectance (i.e. material) we jointly optimize BRDF and illumination together with the object's shape. Our method is class-agnostic and works on in-the-wild image collections of objects to produce relightable 3D assets for several use cases such as AR/VR, movies, games, etc. Project page: https://shinobi.aengelhardt.com Video: https://www.youtube.com/watch?v=iFENQ6AcYd8&feature=youtu.be

Junyi Zhang, Charles Herrmann, Junhwa Hur et al.

Text-to-image diffusion models have made significant advances in generating and editing high-quality images. As a result, numerous approaches have explored the ability of diffusion model features to understand and process single images for downstream tasks, e.g., classification, semantic segmentation, and stylization. However, significantly less is known about what these features reveal across multiple, different images and objects. In this work, we exploit Stable Diffusion (SD) features for semantic and dense correspondence and discover that with simple post-processing, SD features can perform quantitatively similar to SOTA representations. Interestingly, the qualitative analysis reveals that SD features have very different properties compared to existing representation learning features, such as the recently released DINOv2: while DINOv2 provides sparse but accurate matches, SD features provide high-quality spatial information but sometimes inaccurate semantic matches. We demonstrate that a simple fusion of these two features works surprisingly well, and a zero-shot evaluation using nearest neighbors on these fused features provides a significant performance gain over state-of-the-art methods on benchmark datasets, e.g., SPair-71k, PF-Pascal, and TSS. We also show that these correspondences can enable interesting applications such as instance swapping in two images.

Charles Herrmann, Kyle Sargent, Lu Jiang et al.

Aggressive data augmentation is a key component of the strong generalization capabilities of Vision Transformer (ViT). One such data augmentation technique is adversarial training (AT); however, many prior works have shown that this often results in poor clean accuracy. In this work, we present pyramid adversarial training (PyramidAT), a simple and effective technique to improve ViT's overall performance. We pair it with a "matched" Dropout and stochastic depth regularization, which adopts the same Dropout and stochastic depth configuration for the clean and adversarial samples. Similar to the improvements on CNNs by AdvProp (not directly applicable to ViT), our pyramid adversarial training breaks the trade-off between in-distribution accuracy and out-of-distribution robustness for ViT and related architectures. It leads to 1.82% absolute improvement on ImageNet clean accuracy for the ViT-B model when trained only on ImageNet-1K data, while simultaneously boosting performance on 7 ImageNet robustness metrics, by absolute numbers ranging from 1.76% to 15.68%. We set a new state-of-the-art for ImageNet-C (41.42 mCE), ImageNet-R (53.92%), and ImageNet-Sketch (41.04%) without extra data, using only the ViT-B/16 backbone and our pyramid adversarial training. Our code is publicly available at pyramidat.github.io.

Gengshan Yang, Deqing Sun, Varun Jampani et al.

Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature. While template-based approaches, such as parametric shape models, have achieved great success in modeling the "closed world" of known object categories, they cannot well handle the "open-world" of novel object categories or outlier shapes. In this work, we introduce a template-free approach to learn 3D shapes from a single video. It adopts an analysis-by-synthesis strategy that forward-renders object silhouette, optical flow, and pixel values to compare with video observations, which generates gradients to adjust the camera, shape and motion parameters. Without using a category-specific shape template, our method faithfully reconstructs nonrigid 3D structures from videos of human, animals, and objects of unknown classes. Code will be available at lasr-google.github.io .

Deqing Sun, Daniel Vlasic, Charles Herrmann et al.

Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications. To automate the process, we present AutoFlow, a simple and effective method to render training data for optical flow that optimizes the performance of a model on a target dataset. AutoFlow takes a layered approach to render synthetic data, where the motion, shape, and appearance of each layer are controlled by learnable hyperparameters. Experimental results show that AutoFlow achieves state-of-the-art accuracy in pre-training both PWC-Net and RAFT. Our code and data are available at https://autoflow-google.github.io .

Gen Li, Varun Jampani, Laura Sevilla-Lara et al.

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5% in 5-shot segmentation.

Feitong Tan, Danhang Tang, Mingsong Dou et al.

In this paper, we address the problem of building dense correspondences between human images under arbitrary camera viewpoints and body poses. Prior art either assumes small motion between frames or relies on local descriptors, which cannot handle large motion or visually ambiguous body parts, e.g., left vs. right hand. In contrast, we propose a deep learning framework that maps each pixel to a feature space, where the feature distances reflect the geodesic distances among pixels as if they were projected onto the surface of a 3D human scan. To this end, we introduce novel loss functions to push features apart according to their geodesic distances on the surface. Without any semantic annotation, the proposed embeddings automatically learn to differentiate visually similar parts and align different subjects into an unified feature space. Extensive experiments show that the learned embeddings can produce accurate correspondences between images with remarkable generalization capabilities on both intra and inter subjects.

Jialiang Wang, Varun Jampani, Deqing Sun et al.

End-to-end deep learning methods have advanced stereo vision in recent years and obtained excellent results when the training and test data are similar. However, large datasets of diverse real-world scenes with dense ground truth are difficult to obtain and currently not publicly available to the research community. As a result, many algorithms rely on small real-world datasets of similar scenes or synthetic datasets, but end-to-end algorithms trained on such datasets often generalize poorly to different images that arise in real-world applications. As a step towards addressing this problem, we propose to incorporate prior knowledge of scene geometry into an end-to-end stereo network to help networks generalize better. For a given network, we explicitly add a gradient-domain smoothness prior and occlusion reasoning into the network training, while the architecture remains unchanged during inference. Experimentally, we show consistent improvements if we train on synthetic datasets and test on the Middlebury (real images) dataset. Noticeably, we improve PSM-Net accuracy on Middlebury from 5.37 MAE to 3.21 MAE without sacrificing speed.

Taihong Xiao, Jinwei Yuan, Deqing Sun et al.

Cost volume is an essential component of recent deep models for optical flow estimation and is usually constructed by calculating the inner product between two feature vectors. However, the standard inner product in the commonly-used cost volume may limit the representation capacity of flow models because it neglects the correlation among different channel dimensions and weighs each dimension equally. To address this issue, we propose a learnable cost volume (LCV) using an elliptical inner product, which generalizes the standard inner product by a positive definite kernel matrix. To guarantee its positive definiteness, we perform spectral decomposition on the kernel matrix and re-parameterize it via the Cayley representation. The proposed LCV is a lightweight module and can be easily plugged into existing models to replace the vanilla cost volume. Experimental results show that the LCV module not only improves the accuracy of state-of-the-art models on standard benchmarks, but also promotes their robustness against illumination change, noises, and adversarial perturbations of the input signals.

Xitong Yang, Xiaodong Yang, Sifei Liu et al.

One central question for video action recognition is how to model motion. In this paper, we present hierarchical contrastive motion learning, a new self-supervised learning framework to extract effective motion representations from raw video frames. Our approach progressively learns a hierarchy of motion features that correspond to different abstraction levels in a network. This hierarchical design bridges the semantic gap between low-level motion cues and high-level recognition tasks, and promotes the fusion of appearance and motion information at multiple levels. At each level, an explicit motion self-supervision is provided via contrastive learning to enforce the motion features at the current level to predict the future ones at the previous level. Thus, the motion features at higher levels are trained to gradually capture semantic dynamics and evolve more discriminative for action recognition. Our motion learning module is lightweight and flexible to be embedded into various backbone networks. Extensive experiments on four benchmarks show that the proposed approach consistently achieves superior results.

Huaizu Jiang, Deqing Sun, Varun Jampani et al.

We introduce a compact network for holistic scene flow estimation, called SENSE, which shares common encoder features among four closely-related tasks: optical flow estimation, disparity estimation from stereo, occlusion estimation, and semantic segmentation. Our key insight is that sharing features makes the network more compact, induces better feature representations, and can better exploit interactions among these tasks to handle partially labeled data. With a shared encoder, we can flexibly add decoders for different tasks during training. This modular design leads to a compact and efficient model at inference time. Exploiting the interactions among these tasks allows us to introduce distillation and self-supervised losses in addition to supervised losses, which can better handle partially labeled real-world data. SENSE achieves state-of-the-art results on several optical flow benchmarks and runs as fast as networks specifically designed for optical flow. It also compares favorably against the state of the art on stereo and scene flow, while consuming much less memory.

Jinshan Pan, Yang Liu, Deqing Sun et al.

We present a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution. The proposed algorithm first uses a deep neural network to estimate intermediate high-resolution images, blurs the intermediate images using known blur kernels, and then substitutes values of the pixels at the un-decimated positions with those of the corresponding pixels from the low-resolution images. The output of the pixel substitution process strictly satisfies the image formation model and is further refined by the same deep neural network in a cascaded manner. The proposed framework is trained in an end-to-end fashion and can work with existing feed-forward deep neural networks for super-resolution and converges fast in practice. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.

Wei-Sheng Lai, Orazio Gallo, Jinwei Gu et al.

Despite the long history of image and video stitching research, existing academic and commercial solutions still produce strong artifacts. In this work, we propose a wide-baseline video stitching algorithm for linear camera arrays that is temporally stable and tolerant to strong parallax. Our key insight is that stitching can be cast as a problem of learning a smooth spatial interpolation between the input videos. To solve this problem, inspired by pushbroom cameras, we introduce a fast pushbroom interpolation layer and propose a novel pushbroom stitching network, which learns a dense flow field to smoothly align the multiple input videos for spatial interpolation. Our approach outperforms the state-of-the-art by a significant margin, as we show with a user study, and has immediate applications in many areas such as virtual reality, immersive telepresence, autonomous driving, and video surveillance.

Fitsum A. Reda, Deqing Sun, Aysegul Dundar et al.

Learning to synthesize high frame rate videos via interpolation requires large quantities of high frame rate training videos, which, however, are scarce, especially at high resolutions. Here, we propose unsupervised techniques to synthesize high frame rate videos directly from low frame rate videos using cycle consistency. For a triplet of consecutive frames, we optimize models to minimize the discrepancy between the center frame and its cycle reconstruction, obtained by interpolating back from interpolated intermediate frames. This simple unsupervised constraint alone achieves results comparable with supervision using the ground truth intermediate frames. We further introduce a pseudo supervised loss term that enforces the interpolated frames to be consistent with predictions of a pre-trained interpolation model. The pseudo supervised loss term, used together with cycle consistency, can effectively adapt a pre-trained model to a new target domain. With no additional data and in a completely unsupervised fashion, our techniques significantly improve pre-trained models on new target domains, increasing PSNR values from 32.84dB to 33.05dB on the Slowflow and from 31.82dB to 32.53dB on the Sintel evaluation datasets.

Hang Su, Varun Jampani, Deqing Sun et al.

Convolutions are the fundamental building block of CNNs. The fact that their weights are spatially shared is one of the main reasons for their widespread use, but it also is a major limitation, as it makes convolutions content agnostic. We propose a pixel-adaptive convolution (PAC) operation, a simple yet effective modification of standard convolutions, in which the filter weights are multiplied with a spatially-varying kernel that depends on learnable, local pixel features. PAC is a generalization of several popular filtering techniques and thus can be used for a wide range of use cases. Specifically, we demonstrate state-of-the-art performance when PAC is used for deep joint image upsampling. PAC also offers an effective alternative to fully-connected CRF (Full-CRF), called PAC-CRF, which performs competitively, while being considerably faster. In addition, we also demonstrate that PAC can be used as a drop-in replacement for convolution layers in pre-trained networks, resulting in consistent performance improvements.

Varun Jampani, Deqing Sun, Ming-Yu Liu et al.

Superpixels provide an efficient low/mid-level representation of image data, which greatly reduces the number of image primitives for subsequent vision tasks. Existing superpixel algorithms are not differentiable, making them difficult to integrate into otherwise end-to-end trainable deep neural networks. We develop a new differentiable model for superpixel sampling that leverages deep networks for learning superpixel segmentation. The resulting "Superpixel Sampling Network" (SSN) is end-to-end trainable, which allows learning task-specific superpixels with flexible loss functions and has fast runtime. Extensive experimental analysis indicates that SSNs not only outperform existing superpixel algorithms on traditional segmentation benchmarks, but can also learn superpixels for other tasks. In addition, SSNs can be easily integrated into downstream deep networks resulting in performance improvements.

Jinshan Pan, Sifei Liu, Deqing Sun et al.

In this paper, we propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining and dehazing. These problems usually involve the estimation of two components of the target signals: structures and details. Motivated by this, our proposed DualCNN consists of two parallel branches, which respectively recovers the structures and details in an end-to-end manner. The recovered structures and details can generate the target signals according to the formation model for each particular application. The DualCNN is a flexible framework for low-level vision tasks and can be easily incorporated into existing CNNs. Experimental results show that the DualCNN can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods.

Zhaoyang Lv, Kihwan Kim, Alejandro Troccoli et al.

Estimation of 3D motion in a dynamic scene from a temporal pair of images is a core task in many scene understanding problems. In real world applications, a dynamic scene is commonly captured by a moving camera (i.e., panning, tilting or hand-held), increasing the task complexity because the scene is observed from different view points. The main challenge is the disambiguation of the camera motion from scene motion, which becomes more difficult as the amount of rigidity observed decreases, even with successful estimation of 2D image correspondences. Compared to other state-of-the-art 3D scene flow estimation methods, in this paper we propose to \emph{learn} the rigidity of a scene in a supervised manner from a large collection of dynamic scene data, and directly infer a rigidity mask from two sequential images with depths. With the learned network, we show how we can effectively estimate camera motion and projected scene flow using computed 2D optical flow and the inferred rigidity mask. For training and testing the rigidity network, we also provide a new semi-synthetic dynamic scene dataset (synthetic foreground objects with a real background) and an evaluation split that accounts for the percentage of observed non-rigid pixels. Through our evaluation we show the proposed framework outperforms current state-of-the-art scene flow estimation methods in challenging dynamic scenes.

Hang Su, Varun Jampani, Deqing Sun et al.

We present a network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice. Naively applying convolutions on this lattice scales poorly, both in terms of memory and computational cost, as the size of the lattice increases. Instead, our network uses sparse bilateral convolutional layers as building blocks. These layers maintain efficiency by using indexing structures to apply convolutions only on occupied parts of the lattice, and allow flexible specifications of the lattice structure enabling hierarchical and spatially-aware feature learning, as well as joint 2D-3D reasoning. Both point-based and image-based representations can be easily incorporated in a network with such layers and the resulting model can be trained in an end-to-end manner. We present results on 3D segmentation tasks where our approach outperforms existing state-of-the-art techniques.

Huaizu Jiang, Deqing Sun, Varun Jampani et al.

Given two consecutive frames, video interpolation aims at generating intermediate frame(s) to form both spatially and temporally coherent video sequences. While most existing methods focus on single-frame interpolation, we propose an end-to-end convolutional neural network for variable-length multi-frame video interpolation, where the motion interpretation and occlusion reasoning are jointly modeled. We start by computing bi-directional optical flow between the input images using a U-Net architecture. These flows are then linearly combined at each time step to approximate the intermediate bi-directional optical flows. These approximate flows, however, only work well in locally smooth regions and produce artifacts around motion boundaries. To address this shortcoming, we employ another U-Net to refine the approximated flow and also predict soft visibility maps. Finally, the two input images are warped and linearly fused to form each intermediate frame. By applying the visibility maps to the warped images before fusion, we exclude the contribution of occluded pixels to the interpolated intermediate frame to avoid artifacts. Since none of our learned network parameters are time-dependent, our approach is able to produce as many intermediate frames as needed. We use 1,132 video clips with 240-fps, containing 300K individual video frames, to train our network. Experimental results on several datasets, predicting different numbers of interpolated frames, demonstrate that our approach performs consistently better than existing methods.

Zhile Ren, Deqing Sun, Jan Kautz et al.

Given two consecutive frames from a pair of stereo cameras, 3D scene flow methods simultaneously estimate the 3D geometry and motion of the observed scene. Many existing approaches use superpixels for regularization, but may predict inconsistent shapes and motions inside rigidly moving objects. We instead assume that scenes consist of foreground objects rigidly moving in front of a static background, and use semantic cues to produce pixel-accurate scene flow estimates. Our cascaded classification framework accurately models 3D scenes by iteratively refining semantic segmentation masks, stereo correspondences, 3D rigid motion estimates, and optical flow fields. We evaluate our method on the challenging KITTI autonomous driving benchmark, and show that accounting for the motion of segmented vehicles leads to state-of-the-art performance.

Laura Sevilla-Lara, Deqing Sun, Varun Jampani et al.

Existing optical flow methods make generic, spatially homogeneous, assumptions about the spatial structure of the flow. In reality, optical flow varies across an image depending on object class. Simply put, different objects move differently. Here we exploit recent advances in static semantic scene segmentation to segment the image into objects of different types. We define different models of image motion in these regions depending on the type of object. For example, we model the motion on roads with homographies, vegetation with spatially smooth flow, and independently moving objects like cars and planes with affine motion plus deviations. We then pose the flow estimation problem using a novel formulation of localized layers, which addresses limitations of traditional layered models for dealing with complex scene motion. Our semantic flow method achieves the lowest error of any published monocular method in the KITTI-2015 flow benchmark and produces qualitatively better flow and segmentation than recent top methods on a wide range of natural videos.