Kevin J. Shih

Rohan Badlani, Rafael Valle, Kevin J. Shih et al.

We work to create a multilingual speech synthesis system which can generate speech with the proper accent while retaining the characteristics of an individual voice. This is challenging to do because it is expensive to obtain bilingual training data in multiple languages, and the lack of such data results in strong correlations that entangle speaker, language, and accent, resulting in poor transfer capabilities. To overcome this, we present a multilingual, multiaccented, multispeaker speech synthesis model based on RADTTS with explicit control over accent, language, speaker and fine-grained $F_0$ and energy features. Our proposed model does not rely on bilingual training data. We demonstrate an ability to control synthesized accent for any speaker in an open-source dataset comprising of 7 accents. Human subjective evaluation demonstrates that our model can better retain a speaker's voice and accent quality than controlled baselines while synthesizing fluent speech in all target languages and accents in our dataset.

Arushi Goel, Sreyan Ghosh, Vatsal Agarwal et al.

Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and complex videos remains largely unexplored. We introduce MMOU, a new benchmark designed to systematically evaluate multimodal understanding and reasoning under these challenging, real-world conditions. MMOU consists of 15,000 carefully curated questions paired with 9038 web-collected videos of varying length, spanning diverse domains and exhibiting rich, tightly coupled audio-visual content. The benchmark covers 13 fundamental skill categories, all of which require integrating evidence across modalities and time. All questions are manually annotated across multiple turns by professional annotators, ensuring high quality and reasoning fidelity. We evaluate 20+ state-of-the-art open-source and proprietary multimodal models on MMOU. The results expose substantial performance gaps: the best closed-source model achieves only 64.2% accuracy, while the strongest open-source model reaches just 46.8%. Our results highlight the challenges of long-form omni-modal understanding, revealing that current models frequently fail to apply even fundamental skills in long videos. Through detailed analysis, we further identify systematic failure modes and provide insights into where and why current models break.

Nannan Li, Kevin J. Shih, Bryan A. Plummer

Human pose transfer synthesizes new view(s) of a person for a given pose. Recent work achieves this via self-reconstruction, which disentangles a person's pose and texture information by breaking the person down into parts, then recombines them for reconstruction. However, part-level disentanglement preserves some pose information that can create unwanted artifacts. In this paper, we propose Pose Transfer by Permuting Textures (PT$^2$), an approach for self-driven human pose transfer that disentangles pose from texture at the patch-level. Specifically, we remove pose from an input image by permuting image patches so only texture information remains. Then we reconstruct the input image by sampling from the permuted textures for patch-level disentanglement. To reduce noise and recover clothing shape information from the permuted patches, we employ encoders with multiple kernel sizes in a triple branch network. On DeepFashion and Market-1501, PT$^2$ reports significant gains on automatic metrics over other self-driven methods, and even outperforms some fully-supervised methods. A user study also reports images generated by our method are preferred in 68% of cases over self-driven approaches from prior work. Code is available at https://github.com/NannanLi999/pt_square.

Rohan Badlani, Akshit Arora, Subhankar Ghosh et al. · nvidia

We introduce VANI, a very lightweight multi-lingual accent controllable speech synthesis system. Our model builds upon disentanglement strategies proposed in RADMMM and supports explicit control of accent, language, speaker and fine-grained $F_0$ and energy features for speech synthesis. We utilize the Indic languages dataset, released for LIMMITS 2023 as part of ICASSP Signal Processing Grand Challenge, to synthesize speech in 3 different languages. Our model supports transferring the language of a speaker while retaining their voice and the native accent of the target language. We utilize the large-parameter RADMMM model for Track $1$ and lightweight VANI model for Track $2$ and $3$ of the competition.

Kevin J. Shih, Rafael Valle, Rohan Badlani et al.

Despite recent advances in generative modeling for text-to-speech synthesis, these models do not yet have the same fine-grained adjustability of pitch-conditioned deterministic models such as FastPitch and FastSpeech2. Pitch information is not only low-dimensional, but also discontinuous, making it particularly difficult to model in a generative setting. Our work explores several techniques for handling the aforementioned issues in the context of Normalizing Flow models. We also find this problem to be very well suited for Neural Spline flows, which is a highly expressive alternative to the more common affine-coupling mechanism in Normalizing Flows.

Tingle Li, Siddharth Gururani, Kevin J. Shih et al.

Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical processes. Existing evaluations emphasize perceptual realism and overlook physical correctness under controlled interventions. In this paper, we introduce FlatSounds, a benchmark that audits the physical reasoning of V2A models through: 1) controlled counterfactual pairs in which a single physical factor is varied, and 2) single-video pattern tests that probe internal consistency and directional trends. These settings test whether the generated audio correctly reflects specific physical properties and timings. Our evaluation of state-of-the-art models reveals a consistent trade-off: models rely more on text captions than the visual stream to infer physics and semantics. Captions generally improve physical and semantic accuracy, but paradoxically degrade temporal alignment. Our results highlight the need to move beyond audio quality toward learning physical processes directly from pixels. Finally, we find that our physics-based metrics correlate strongly with human preference tests on our own data. Project webpage: https://research.nvidia.com/labs/cosmos-lab/flatsounds/

Nannan Li, Kevin J. Shih, Bryan A. Plummer

Given an isolated garment image in a canonical product view and a separate image of a person, the virtual try-on task aims to generate a new image of the person wearing the target garment. Prior virtual try-on works face two major challenges in achieving this goal: a) the paired (human, garment) training data has limited availability; b) generating textures on the human that perfectly match that of the prompted garment is difficult, often resulting in distorted text and faded textures. Our work explores ways to tackle these issues through both synthetic data as well as model refinement. We introduce a garment extraction model that generates (human, synthetic garment) pairs from a single image of a clothed individual. The synthetic pairs can then be used to augment the training of virtual try-on. We also propose an Error-Aware Refinement-based Schrödinger Bridge (EARSB) that surgically targets localized generation errors for correcting the output of a base virtual try-on model. To identify likely errors, we propose a weakly-supervised error classifier that localizes regions for refinement, subsequently augmenting the Schrödinger Bridge's noise schedule with its confidence heatmap. Experiments on VITON-HD and DressCode-Upper demonstrate that our synthetic data augmentation enhances the performance of prior work, while EARSB improves the overall image quality. In user studies, our model is preferred by the users in an average of 59% of cases.

Rohan Badlani, Adrian Łancucki, Kevin J. Shih et al.

Speech-to-text alignment is a critical component of neural textto-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-line. However, these alignments tend to be brittle and often fail to generalize to long utterances and out-of-domain text, leading to missing or repeating words. Most non-autoregressive endto-end TTS models rely on durations extracted from external sources. In this paper we leverage the alignment mechanism proposed in RAD-TTS as a generic alignment learning framework, easily applicable to a variety of neural TTS models. The framework combines forward-sum algorithm, the Viterbi algorithm, and a simple and efficient static prior. In our experiments, the alignment learning framework improves all tested TTS architectures, both autoregressive (Flowtron, Tacotron 2) and non-autoregressive (FastPitch, FastSpeech 2, RAD-TTS). Specifically, it improves alignment convergence speed of existing attention-based mechanisms, simplifies the training pipeline, and makes the models more robust to errors on long utterances. Most importantly, the framework improves the perceived speech synthesis quality, as judged by human evaluators.

Aysegul Dundar, Kevin J. Shih, Animesh Garg et al.

Unsupervised landmark learning is the task of learning semantic keypoint-like representations without the use of expensive input keypoint-level annotations. A popular approach is to factorize an image into a pose and appearance data stream, then to reconstruct the image from the factorized components. The pose representation should capture a set of consistent and tightly localized landmarks in order to facilitate reconstruction of the input image. Ultimately, we wish for our learned landmarks to focus on the foreground object of interest. However, the reconstruction task of the entire image forces the model to allocate landmarks to model the background. This work explores the effects of factorizing the reconstruction task into separate foreground and background reconstructions, conditioning only the foreground reconstruction on the unsupervised landmarks. Our experiments demonstrate that the proposed factorization results in landmarks that are focused on the foreground object of interest. Furthermore, the rendered background quality is also improved, as the background rendering pipeline no longer requires the ill-suited landmarks to model its pose and appearance. We demonstrate this improvement in the context of the video-prediction task.

Kevin J. Shih, Aysegul Dundar, Animesh Garg et al.

Prediction and interpolation for long-range video data involves the complex task of modeling motion trajectories for each visible object, occlusions and dis-occlusions, as well as appearance changes due to viewpoint and lighting. Optical flow based techniques generalize but are suitable only for short temporal ranges. Many methods opt to project the video frames to a low dimensional latent space, achieving long-range predictions. However, these latent representations are often non-interpretable, and therefore difficult to manipulate. This work poses video prediction and interpolation as unsupervised latent structure inference followed by a temporal prediction in this latent space. The latent representations capture foreground semantics without explicit supervision such as keypoints or poses. Further, as each landmark can be mapped to a coordinate indicating where a semantic part is positioned, we can reliably interpolate within the coordinate domain to achieve predictable motion interpolation. Given an image decoder capable of mapping these landmarks back to the image domain, we are able to achieve high-quality long-range video interpolation and extrapolation by operating on the landmark representation space.

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.

Ji Zhang, Kevin J. Shih, Ahmed Elgammal et al.

Most scene graph parsers use a two-stage pipeline to detect visual relationships: the first stage detects entities, and the second predicts the predicate for each entity pair using a softmax distribution. We find that such pipelines, trained with only a cross entropy loss over predicate classes, suffer from two common errors. The first, Entity Instance Confusion, occurs when the model confuses multiple instances of the same type of entity (e.g. multiple cups). The second, Proximal Relationship Ambiguity, arises when multiple subject-predicate-object triplets appear in close proximity with the same predicate, and the model struggles to infer the correct subject-object pairings (e.g. mis-pairing musicians and their instruments). We propose a set of contrastive loss formulations that specifically target these types of errors within the scene graph parsing problem, collectively termed the Graphical Contrastive Losses. These losses explicitly force the model to disambiguate related and unrelated instances through margin constraints specific to each type of confusion. We further construct a relationship detector, called RelDN, using the aforementioned pipeline to demonstrate the efficacy of our proposed losses. Our model outperforms the winning method of the OpenImages Relationship Detection Challenge by 4.7\% (16.5\% relative) on the test set. We also show improved results over the best previous methods on the Visual Genome and Visual Relationship Detection datasets.

Yi Zhu, Karan Sapra, Fitsum A. Reda et al.

Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to improve the accuracy of semantic segmentation networks. We exploit video prediction models' ability to predict future frames in order to also predict future labels. A joint propagation strategy is also proposed to alleviate mis-alignments in synthesized samples. We demonstrate that training segmentation models on datasets augmented by the synthesized samples leads to significant improvements in accuracy. Furthermore, we introduce a novel boundary label relaxation technique that makes training robust to annotation noise and propagation artifacts along object boundaries. Our proposed methods achieve state-of-the-art mIoUs of 83.5% on Cityscapes and 82.9% on CamVid. Our single model, without model ensembles, achieves 72.8% mIoU on the KITTI semantic segmentation test set, which surpasses the winning entry of the ROB challenge 2018. Our code and videos can be found at https://nv-adlr.github.io/publication/2018-Segmentation.

Guilin Liu, Kevin J. Shih, Ting-Chun Wang et al.

In this paper, we present a simple yet effective padding scheme that can be used as a drop-in module for existing convolutional neural networks. We call it partial convolution based padding, with the intuition that the padded region can be treated as holes and the original input as non-holes. Specifically, during the convolution operation, the convolution results are re-weighted near image borders based on the ratios between the padded area and the convolution sliding window area. Extensive experiments with various deep network models on ImageNet classification and semantic segmentation demonstrate that the proposed padding scheme consistently outperforms standard zero padding with better accuracy.

Bryan A. Plummer, Kevin J. Shih, Yichen Li et al.

Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image. In this paper we address a more realistic version of the natural language grounding task where we must both identify whether the phrase is relevant to an image and localize the phrase. This can also be viewed as a generalization of object detection to an open-ended vocabulary, introducing elements of few- and zero-shot detection. We propose an approach for this task that extends Faster R-CNN to relate image regions and phrases. By carefully initializing the classification layers of our network using canonical correlation analysis (CCA), we encourage a solution that is more discerning when reasoning between similar phrases, resulting in over double the performance compared to a naive adaptation on three popular phrase grounding datasets, Flickr30K Entities, ReferIt Game, and Visual Genome, with test-time phrase vocabulary sizes of 5K, 32K, and 159K, respectively.

Fitsum A. Reda, Guilin Liu, Kevin J. Shih et al.

We present an approach for high-resolution video frame prediction by conditioning on both past frames and past optical flows. Previous approaches rely on resampling past frames, guided by a learned future optical flow, or on direct generation of pixels. Resampling based on flow is insufficient because it cannot deal with disocclusions. Generative models currently lead to blurry results. Recent approaches synthesis a pixel by convolving input patches with a predicted kernel. However, their memory requirement increases with kernel size. Here, we spatially-displaced convolution (SDC) module for video frame prediction. We learn a motion vector and a kernel for each pixel and synthesize a pixel by applying the kernel at a displaced location in the source image, defined by the predicted motion vector. Our approach inherits the merits of both vector-based and kernel-based approaches, while ameliorating their respective disadvantages. We train our model on 428K unlabelled 1080p video game frames. Our approach produces state-of-the-art results, achieving an SSIM score of 0.904 on high-definition YouTube-8M videos, 0.918 on Caltech Pedestrian videos. Our model handles large motion effectively and synthesizes crisp frames with consistent motion.

Guilin Liu, Fitsum A. Reda, Kevin J. Shih et al.

Existing deep learning based image inpainting methods use a standard convolutional network over the corrupted image, using convolutional filter responses conditioned on both valid pixels as well as the substitute values in the masked holes (typically the mean value). This often leads to artifacts such as color discrepancy and blurriness. Post-processing is usually used to reduce such artifacts, but are expensive and may fail. We propose the use of partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels. We further include a mechanism to automatically generate an updated mask for the next layer as part of the forward pass. Our model outperforms other methods for irregular masks. We show qualitative and quantitative comparisons with other methods to validate our approach.

Yonatan Bisk, Kevin J. Shih, Yejin Choi et al.

In this paper, we study the problem of mapping natural language instructions to complex spatial actions in a 3D blocks world. We first introduce a new dataset that pairs complex 3D spatial operations to rich natural language descriptions that require complex spatial and pragmatic interpretations such as "mirroring", "twisting", and "balancing". This dataset, built on the simulation environment of Bisk, Yuret, and Marcu (2016), attains language that is significantly richer and more complex, while also doubling the size of the original dataset in the 2D environment with 100 new world configurations and 250,000 tokens. In addition, we propose a new neural architecture that achieves competitive results while automatically discovering an inventory of interpretable spatial operations (Figure 5)

Kevin J. Shih, Saurabh Singh, Derek Hoiem

We present a method that learns to answer visual questions by selecting image regions relevant to the text-based query. Our method exhibits significant improvements in answering questions such as "what color," where it is necessary to evaluate a specific location, and "what room," where it selectively identifies informative image regions. Our model is tested on the VQA dataset which is the largest human-annotated visual question answering dataset to our knowledge.

Kevin J. Shih, Arun Mallya, Saurabh Singh et al.

We present a simple deep learning framework to simultaneously predict keypoint locations and their respective visibilities and use those to achieve state-of-the-art performance for fine-grained classification. We show that by conditioning the predictions on object proposals with sufficient image support, our method can do well without complicated spatial reasoning. Instead, inference methods with robustness to outliers, yield state-of-the-art for keypoint localization. We demonstrate the effectiveness of our accurate keypoint localization and visibility prediction on the fine-grained bird recognition task with and without ground truth bird bounding boxes, and outperform existing state-of-the-art methods by over 2%.