{"id":"7c5d8e24-d6c4-4241-8ece-f28bee085636","arxiv_id":"2605.02849","paper_version":2,"verdict":"UNVERDICTED","confidence":"LOW","novelty_score":5.0,"correctness_risk":"unknown","formal_verification":"none","parameter_count":0,"one_line_summary":"ActDiff-VC partitions video into segments, transmits adaptive keyframes and budget-aware point trajectories, and reconstructs frames via conditional diffusion, reporting up to 64.6% bitrate reduction at matched NIQE on UVG and MCL-JCV.","lead":"ActDiff-VC is a diffusion-based video compression system that sends only sparse keyframes and tracked point trajectories, then uses a conditional diffusion model to generate the rest of the frames. This targets ultra-low bitrates where traditional codecs fail to maintain perceptual quality.","discovery_kind":"new_method","skeptic_critique":{"model":"grok-4.3","headline":"No significant objection identified","rationale":"The reader's weakest assumption correctly isolates the central unverified step. Because the full text was not supplied for this pass, no additional load-bearing technical flaw (e.g., hidden assumption in an equation or flawed experimental control) can be identified.","tokens_in":1729,"tokens_out":228,"duration_ms":23338,"concrete_test":"Re-run the reported UVG/MCL-JCV comparisons after replacing the diffusion decoder with a deterministic interpolation baseline that uses the identical keyframe and trajectory conditioning; if the perceptual metrics (NIQE/KID/FID) remain comparable, the generative prior is not the source of the reported gains.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The abstract presents a coherent design (content-adaptive keyframes + budget-aware trajectories as conditioning for a diffusion decoder) and reports concrete benchmark numbers on UVG/MCL-JCV. Without the full manuscript the precise implementation details, training procedure, and ablation results cannot be examined, but nothing in the stated claim is internally inconsistent or relies on an obviously false premise.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.3","summary":"The paper proposes ActDiff-VC, a diffusion-based video compression method for the ultra-low-bitrate regime. Videos are partitioned into variable-length segments; content-adaptive keyframes and budget-aware sparse point trajectories are transmitted as compact conditioning signals to a conditional diffusion decoder that synthesizes the omitted frames. Experiments on UVG and MCL-JCV are reported to show up to 64.6% bitrate reduction at matched NIQE, with corresponding gains in KID (up to 64.6%) and FID (up to 37.7%) versus strong learned codecs.","tokens_in":1772,"tokens_out":519,"duration_ms":23173,"significance":"If the empirical claims are substantiated with full protocols, the work would demonstrate that controlled diffusion models can deliver perceptually superior reconstructions at bitrates where conventional codecs fail, using only sparse, actively selected conditioning. The combination of content-adaptive keyframe selection and trajectory-based temporal summarization is a concrete technical contribution that could influence future generative compression pipelines.","major_comments":[{"comment":"The abstract states concrete benchmark numbers (64.6% bitrate reduction, KID/FID gains) on UVG and MCL-JCV yet supplies no experimental protocol, baseline implementation details, training procedure, number of runs, or error bars. The methods and results sections must furnish these elements; without them the central empirical claim cannot be evaluated.","section":"Abstract / Experimental Results"},{"comment":"The conditioning mechanism (sparse keyframes + tracked point trajectories fed to the diffusion decoder) is described at a high level; the paper must specify the exact form of the conditioning signals, the diffusion architecture, training objective, and inference procedure to confirm that the reported perceptual gains are not artifacts of an overfitted or improperly conditioned model.","section":"Method / Conditioning Design"}],"minor_comments":[{"comment":"Clarify the precise definition of 'ultra-low-bitrate regime' (target bpp range) and how it is enforced during both training and evaluation.","section":"Introduction / Experiments"},{"comment":"Add a clear statement of the number of videos, resolutions, and frame counts used from UVG and MCL-JCV.","section":"Experiments"}],"recommendation":"major_revision","confidential_remarks":"The manuscript is an arXiv preprint; the experimental reporting gap is the primary concern for a journal that requires reproducible results. No other red flags in citation pattern or scope."},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for the constructive comments on our manuscript. We address each major comment below and will revise the manuscript to supply the requested details.","responses":[{"response":"We agree that full experimental protocols, baseline implementation details, training procedures, number of runs, and error bars belong in the methods and results sections. While abstracts conventionally omit such details for brevity, the current manuscript lacks sufficient specification in those sections. In the revision we will expand the experimental section with complete baseline implementations, training protocols, run counts, and error bars on all reported metrics.","revision_made":"yes","referee_comment":"[Abstract / Experimental Results] The abstract states concrete benchmark numbers (64.6% bitrate reduction, KID/FID gains) on UVG and MCL-JCV yet supplies no experimental protocol, baseline implementation details, training procedure, number of runs, or error bars. The methods and results sections must furnish these elements; without them the central empirical claim cannot be evaluated."},{"response":"We agree that the conditioning signals, diffusion architecture, training objective, and inference procedure are currently described at a high level. In the revised manuscript we will add the precise mathematical form of the conditioning (keyframe and trajectory encoding and injection), the diffusion network architecture and conditioning modules, the training objective, and the full inference procedure including sampling steps and guidance parameters.","revision_made":"yes","referee_comment":"[Method / Conditioning Design] The conditioning mechanism (sparse keyframes + tracked point trajectories fed to the diffusion decoder) is described at a high level; the paper must specify the exact form of the conditioning signals, the diffusion architecture, training objective, and inference procedure to confirm that the reported perceptual gains are not artifacts of an overfitted or improperly conditioned model."}],"tokens_in":1391,"tokens_out":389,"duration_ms":31311,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The main point is that this paper builds a video compression system around a conditional diffusion decoder that receives only sparse keyframes and tracked point trajectories instead of dense frames. The two active sampling pieces—content-adaptive keyframe placement and budget-aware trajectory selection—are presented as the practical knobs that keep the side information small while still letting the generative model produce the missing frames.\n\nWhat the work actually contributes is the specific pairing of those sampling rules inside a diffusion pipeline for the ultra-low-bitrate setting. The experiments run on UVG and MCL-JCV and claim up to 64.6% bitrate reduction at matched NIQE plus clear lifts in KID and FID against learned codecs and other diffusion baselines.\n\nThe soft spots are straightforward. The abstract gives no protocol details, no description of how the trajectories are extracted or encoded, no training recipe, and no ablations that isolate the contribution of each sampling step. The repeated 64.6% figure across different metrics also looks like a reporting slip. Those gaps make it hard to judge whether the gains are robust or sensitive to the particular test sequences.\n\nThe central assumption—that the chosen sparse signals are sufficient conditioning—does not contain an obvious contradiction, and the design is internally consistent. A reader working on perceptual codecs or diffusion-based coding would find the benchmark comparisons useful even if they later modify the sampling logic.\n\nI would send this to peer review. The idea is concrete, the claims are testable on public data, and the gaps are the normal kind that referees can ask the authors to close.","headline":"ActDiff-VC pairs content-adaptive keyframes with budget-aware point trajectories to condition a diffusion decoder, delivering reported perceptual gains at ultra-low rates on standard benchmarks.","tokens_in":2260,"tokens_out":390,"would_cite":false,"duration_ms":36258,"reading_group":"maybe","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"grok-4.3","headline":"ActDiff-VC achieves up to 64.6% bitrate reduction in video by conditioning a diffusion decoder on sparse keyframes and tracked point trajectories.","keywords":["video compression","diffusion models","ultra-low bitrate","keyframe selection","point trajectories","conditional generation","perceptual quality"],"falsifier":"A set of test videos where the synthesized frames exhibit visible artifacts or fail to match the reported perceptual metric gains even when the same keyframes and trajectories are supplied at the claimed bitrates.","tokens_in":2629,"feed_emoji":"📹","tokens_out":638,"duration_ms":24872,"temperature":0.7,"pith_summary":"The paper introduces ActDiff-VC as a diffusion-based method that compresses video at ultra-low bitrates by sending only adaptively chosen keyframes and a compact set of tracked point trajectories. These signals then control a conditional diffusion decoder to generate the omitted frames. A sympathetic reader would care because the approach targets regimes where conventional codecs produce unacceptable quality, potentially enabling usable video in severely bandwidth-constrained settings. Experiments on standard benchmarks demonstrate the resulting perceptual gains over learned codecs.","feed_headline":"Diffusion codec cuts video bitrates up to 64% at matched quality","feed_subtitle":"Sparse keyframes and point tracks let a conditional diffusion decoder synthesize realistic missing frames.","key_machinery":"The conditional diffusion decoder guided by sparse keyframes and tracked point trajectories, which uses these compact signals to control frame synthesis.","core_discovery":"ActDiff-VC partitions videos into variable-length segments, transmits keyframes only when needed, and summarizes temporal dynamics using a compact set of tracked point trajectories. Conditioned on these sparse signals, a conditional diffusion decoder synthesizes the remaining frames. This design, supported by content-adaptive keyframe selection and budget-aware sparse trajectory selection, enables perceptually realistic reconstruction under severe rate constraints and yields up to 64.6% bitrate reduction at matched NIQE along with KID and FID improvements on the UVG and MCL-JCV benchmarks.","pith_inferences":["The same active-sampling idea could be tested on other generative compression tasks such as audio or volumetric video.","Hardware acceleration of the diffusion sampling step would be needed to move the method from offline to real-time use.","The results imply that minimal explicit motion cues plus a strong generative prior can outperform predictive coding when rates drop below conventional operating points."],"forward_implications":["Enables up to 64.6% bitrate reduction at matched NIQE compared with strong learned codecs.","Improves KID by up to 64.6% and FID by up to 37.7% at comparable bitrates.","Delivers favorable perceptual rate-distortion trade-offs relative to learned and diffusion-based baselines in the ultra-low-bitrate regime."],"fun_headline_variants":["ActDiff-VC uses tracked points for ultra low bitrate video diffusion","Diffusion decoder reconstructs video from sparse keyframes and trajectories","Variable segment keyframe selection achieves 64 percent bitrate reduction","Budget aware trajectory sampling conditions diffusion for video compression"],"cache_read_input_tokens":64,"weakest_assumption_plain":"That conditioning the diffusion decoder on the selected sparse keyframes and tracked point trajectories is enough to produce perceptually realistic reconstructions of the omitted frames.","fun_headline_variants_meta":{"raw":{"variants":["ActDiff-VC uses tracked points for ultra low bitrate video diffusion","Diffusion decoder reconstructs video from sparse keyframes and trajectories","Variable segment keyframe selection achieves 64 percent bitrate reduction","Budget aware trajectory sampling conditions diffusion for video compression"]},"model":"grok-4.3","cost_usd":0.006046,"raw_usage":{"total_tokens":2868,"prompt_tokens":684,"num_sources_used":0,"completion_tokens":64,"cost_in_usd_ticks":60462000,"prompt_tokens_details":{"text_tokens":684,"audio_tokens":0,"image_tokens":0,"cached_tokens":256},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":2120,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":684,"tokens_out":64,"duration_ms":18022,"temperature":1.0,"reasoning_tokens":2120,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-07-01T00:16:48.230119+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"A set of test videos where the synthesized frames exhibit visible artifacts or fail to match the reported perceptual metric gains even when the same keyframes and trajectories are supplied at the claimed bitrates.","supporting_citations":[],"review_version":2}